NAACL HLT 2015 Main Program Schedule

This schedule is interactive, you can click on a session to view the talks in that session, and you can click on a talk to see its abstract. However, if you want to search for a specific talk in the schedule, you should expand all sessions first.

Monday, June 1


Registration and Breakfast


Welcome to NAACL HLT 2015


Invited Talk by Lillian Lee: "Big data pragmatics!", or, "Putting the ACL in computational social science", or, if you think these title alternatives could turn people on, turn people off, or otherwise have an effect, this talk might be for you. — Plaza Ballroom A, B & C

Slides: PDF

Chair: Rada Mihalcea, University of Michigan

What effect does language have on people?

You might say in response, "Who are you to discuss this problem?" and you would be right to do so; this is a Major Question that science has been tackling for many years. But as a field, I think natural language processing and computational linguistics have much to contribute to the conversation, and I hope to encourage the community to further address these issues.

This talk will focus on the effect of phrasing, emphasizing aspects that go beyond just the selection of one particular word over another. The issues we'll consider include: Does the way in which something is worded in and of itself have an effect on whether it is remembered or attracts attention, beyond its content or context? Can we characterize how different sides in a debate frame their arguments, in a way that goes beyond specific lexical choice (e.g., "pro-choice" vs. "pro-life")? The settings we'll explore range from movie quotes that achieve cultural prominence; to posts on Facebook, Wikipedia, Twitter, and the arXiv; to framing in public discourse on the inclusion of genetically-modified organisms in food.

Joint work with Lars Backstrom, Justin Cheng, Eunsol Choi, Cristian Danescu-Niculescu-Mizil, Jon Kleinberg, Bo Pang, Jennifer Spindel, and Chenhao Tan.




1A: Semantics (Long Papers) — Plaza Ballroom A & B

Chair: Hoifung Poon, Microsoft Research

1B: Tagging, Chunking, Syntax and Parsing (Long + TACL Papers) — Plaza Ballroom D & E

Chair: Noah Smith, Carnegie Mellon University

1C: Information Retrieval, Text Categorization, Topic Modeling (Long Papers) — Plaza Ballroom F

Chair: Jordan Boyd-Graber, University of Colorado


455: Unsupervised Induction of Semantic Roles within a Reconstruction-Error Minimization Framework, by Ivan Titov and Ehsan Khoddam

We introduce a new approach to unsupervised estimation of feature-rich semantic role labeling models. Our model consists of two components: (1) an encoding component: a semantic role labeling model which predicts roles given a rich set of syntactic and lexical features; (2) a reconstruction component: a tensor factorization model which relies on roles to predict argument fillers. When the components are estimated jointly to minimize errors in argument reconstruction, the induced roles largely correspond to roles defined in annotated resources. Our method performs on par with most accurate role induction methods on English and German, even though, unlike these previous approaches, we do not incorporate any prior linguistic knowledge about the languages.

TACL-488: Exploring Compositional Architectures and Word Vector Representations for Prepositional Phrase Attachment, by Yonatan Belinkov, Tao Lei, Regina Barzilay, Amir Globerson

Prepositional phrase (PP) attachment disambiguation is a known challenge in syntactic parsing. The lexical sparsity associated with PP attachments motivates research in word representations that can capture pertinent syntactic and semantic features of the word. One promising solution is to use word vectors induced from large amounts of raw text. However, state-of-the-art systems that employ such representations yield modest gains in PP attachment accuracy. In this paper, we show that word vector representations can yield significant PP attachment performance gains. This is achieved via a non-linear architecture that is discriminatively trained to maximize PP attachment accuracy. The architecture is initialized with word vectors trained from unlabeled data, and relearns those to maximize attachment accuracy. We obtain additional performance gains with alternative representations such as dependency-based word vectors. When tested on both English and Arabic datasets, our method outperforms both a strong SVM classifier and state-of-the-art parsers. For instance, we achieve 82.6% PP attachment accuracy on Arabic, while the Turbo and Charniak self-trained parsers obtain 76.7% and 80.8% respectively.

533: A Hybrid Generative/Discriminative Approach To Citation Prediction, by Chris Tanner and Eugene Charniak

Text documents of varying nature (e.g., summary documents written by analysts or published, scientific papers) often cite others as a means of providing evidence to support a claim, attributing credit, or referring the reader to related work. We address the problem of predicting a document's cited sources by introducing a novel, discriminative approach which combines a content-based generative model (LDA) with author-based features. Further, our classifier is able to learn the importance and quality of each topic within our corpus -- which can be useful beyond this task -- and preliminary results suggest its metric is competitive with other standard metrics (Topic Coherence). Our flagship system, Logit-Expanded, provides state-of-the-art performance on the largest corpus ever used for this task.


550: Predicate Argument Alignment using a Global Coherence Model, by Travis Wolfe, Mark Dredze, Benjamin Van Durme

We present a joint model for predicate argument alignment. We leverage multiple sources of semantic information, including temporal ordering constraints between events. These are combined in a max-margin framework to find a globally consistent view of entities and events across multiple documents, which leads to improvements on the state-of-the-art.

136: An Incremental Algorithm for Transition-based CCG Parsing, by Bharat Ram Ambati, Tejaswini Deoskar, Mark Johnson, Mark Steedman

Incremental parsers have potential advantages for applications like language modeling for machine translation and speech recognition. We describe a new algorithm for incremental transition-based Combinatory Categorial Grammar parsing. As English CCGbank derivations are mostly right branching and non-incremental, we design our algorithm based on the dependencies resolved rather than the derivation. We introduce two new actions in the shift-reduce paradigm based on the idea of ‘revealing’ (Pareschi and Steedman, 1987) the required information during parsing. On the standard CCGbank test data, our algorithm achieved improvements of 0.88% in labeled and 2.0% in unlabeled F-score over a greedy non-incremental shift-reduce parser.

634: Weakly Supervised Slot Tagging with Partially Labeled Sequences from Web Search Click Logs, by Young-Bum Kim, Minwoo Jeong, Karl Stratos, Ruhi Sarikaya

In this paper, we apply a weakly-supervised learning approach for slot tagging using con- ditional random fields by exploiting web search click logs. We extend the constrained lattice training of Täckström et al. (2013) to non-linear conditional random fields in which latent variables mediate between observations and labels. When combined with a novel initialization scheme that leverages unlabeled data, we show that our method gives signifi- cant improvement over strong supervised and weakly-supervised baselines.


670: Improving unsupervised vector-space thematic fit evaluation via role-filler prototype clustering, by Clayton Greenberg, Asad Sayeed, Vera Demberg

Most recent unsupervised methods in vector space semantics for assessing thematic fit (e.g. Erk, 2007; Baroni and Lenci, 2010; Sayeed and Demberg, 2014) create prototypical role-fillers without performing word sense disambiguation. This leads to a kind of sparsity problem: candidate role-fillers for different senses of the verb end up being measured by the same “yardstick”, the single prototypical role-filler.

In this work, we use three different feature spaces to construct robust unsupervised models of distributional semantics. We show that correlation with human judgements on thematic fit estimates can be improved consistently by clustering typical role-fillers and then calculating similarities of candidate role-fillers with these cluster centroids. The suggested methods can be used in any vector space model that constructs a prototype vector from a non-trivial set of typical vectors.

540: Because Syntax Does Matter: Improving Predicate-Argument Structures Parsing with Syntactic Features, by Corentin Ribeyre, Eric Villemonte de la Clergerie, Djamé Seddah

Parsing full-fledged predicate-argument structures in a deep syntax framework requires graphs to be predicted. Using the DeepBank (Flickinger et al., 2012) and the Predicate-Argument Structure treebank (Miyao and Tsujii, 2005) as a test field, we show how transition-based parsers, extended to handle connected graphs, benefit from the use of topologically different syntactic features such as dependencies, tree fragments, spines or syntactic paths, bringing a much needed context to the parsing models, improving notably over long distance dependencies and elided coordinate structures. By confirming this positive impact on an accurate 2nd-order graph-based parser (Martins and Almeida, 2014), we establish a new state-of-the-art on these data sets.

353: Not All Character N-grams Are Created Equal: A Study in Authorship Attribution, by Upendra Sapkota, Steven Bethard, Manuel Montes, Thamar Solorio

Character n-grams have been identified as the most successful feature in both single-domain and cross-domain Authorship Attribution (AA), but the reasons for their discriminative value were not fully understood. We identify subgroups of character n-grams that correspond to linguistic aspects commonly claimed to be covered by these features: morpho-syntax, thematic content and style. We evaluate the predictiveness of each of these groups in two AA settings: a single domain setting and a cross-domain setting where multiple topics are present. We demonstrate that character $n$-grams that capture information about affixes and punctuation account for almost all of the power of character n-grams as features. Our study contributes new insights into the use of n-grams for future AA work and other classification tasks.


411: A Compositional and Interpretable Semantic Space, by Alona Fyshe, Leila Wehbe, Partha P. Talukdar, Brian Murphy, Tom M. Mitchell

Vector Space Models (VSMs) of Semantics are useful tools for exploring the semantics of single words, and the composition of words to make phrasal meaning. While many methods can estimate the meaning (i.e. vector) of a phrase, few do so in an interpretable way. We introduce a new method (CNNSE) that allows word and phrase vectors to adapt to the notion of composition. Our method learns a VSM that is both tailored to support a chosen semantic composition operation, and whose resulting features have an intuitive interpretation. Interpretability allows for the exploration of phrasal semantics, which we leverage to analyze performance on a behavioral task.

560: Randomized Greedy Inference for Joint Segmentation, POS Tagging and Dependency Parsing, by Yuan Zhang, Chengtao Li, Regina Barzilay, Kareem Darwish

In this paper, we introduce a new approach for joint segmentation, POS tagging and dependency parsing. While joint modeling of these tasks addresses the issue of error propagation inherent in traditional pipeline architectures, it also complicates the inference task. Past research has addressed this challenge by placing constraints on the scoring function. In contrast, we propose an approach that can handle arbitrarily complex scoring functions. Specifically, we employ a randomized greedy algorithm that jointly predicts segmentations, POS tags and dependency trees. Moreover, this architecture readily handles different segmentation tasks, such as morphological segmentation for Arabic and word segmentation for Chinese. The joint model outperforms the state-of-the-art systems on three datasets, obtaining 2.1% TedEval absolute gain against the best published results in the 2013 SPMRL shared task.

73: Effective Use of Word Order for Text Categorization with Convolutional Neural Networks, by Rie Johnson and Tong Zhang

Convolutional neural network (CNN) is a neural network that can make use of the internal structure of data such as the 2D structure of image data. This paper studies CNN on text categorization to exploit the 1D structure (namely, word order) of text data for accurate prediction. Instead of using low-dimensional word vectors as input as is often done, we directly apply CNN to high-dimensional text data, which leads to directly learning embedding of small text regions for use in classification. In addition to a straightforward adaptation of CNN from image to text, a simple but new variation which employs bag-of-word conversion in the convolution layer is proposed. An extension to combine multiple convolution layers is also explored for higher accuracy. The experiments demonstrate the effectiveness of our approach in comparison with state-of-the-art methods.




2A: Generation and Summarization (Long Papers) — Plaza Ballroom A & B

Chair: Fei Liu, Carnegie Mellon University

2B: Language and Vision (Long Papers) — Plaza Ballroom D & E

Chair: Yejin Choi, University of Washington

2C: NLP for Web, Social Media and Social Sciences (Long Papers) — Plaza Ballroom F

Chair: Tong Zhang, Rutgers University


55: Transition-Based Syntactic Linearization, by Yijia Liu, Yue Zhang, Wanxiang Che, Bing Qin

Syntactic linearization algorithms take a bag of input words and a set of optional constraints, and construct an output sentence and its syntactic derivation simultaneously. The search problem is NP-hard, and the current best results are achieved by bottom-up best-first search.One drawback of the method is low efficiency; and there is no theoretical guarantee that a full sentence can be found within bounded time.We propose an alternative algorithm that constructs output structures from left to right using beam-search.The algorithm is based on incremental parsing algorithms. We extend the transition system so that word ordering is performed in addition to syntactic parsing, resulting in a linearization system that runs in guaranteed quadratic time. In standard evaluations, our system runs an order of magnitude faster than a state-of-the-art baseline using best-first search, with improved accuracies.

182: What’s Cookin’? Interpreting Cooking Videos using Text, Speech and Vision, by Jonathan Malmaud, Jonathan Huang, Vivek Rathod, Nicholas Johnston, Andrew Rabinovich, Kevin Murphy

We present a novel method for aligning a sequence of instructions to a video of someone carrying out a task. In particular, we focus on the cooking domain, where the instructions correspond to the recipe. Our technique relies on an HMM to align the recipe steps to the (automatically generated) speech transcript. We then refine this alignment using a state-of-the-art visual food detector, based on a deep convolutional neural network. We show that our technique outperforms simpler techniques based on keyword spotting. It also enables interesting applications, such as automatically illustrating recipes with keyframes, and searching within a video for events of interest.

39: TopicCheck: Interactive Alignment for Assessing Topic Model Stability, by Jason Chuang, Margaret E. Roberts, Brandon M. Stewart, Rebecca Weiss, Dustin Tingley, Justin Grimmer, Jeffrey Heer

Content analysis, a widely-applied social science research method, is increasingly being supplemented by topic modeling. However, while the discourse on content analysis centers heavily on reproducibility, computer scientists often focus more on scalability and less on coding reliability, leading to growing skepticism on the usefulness of topic models for automated content analysis. In response, we introduce TopicCheck, an interactive tool for assessing topic model stability. Our contributions are threefold. First, from established guidelines on reproducible content analysis, we distill a set of design requirements on how to computationally assess the stability of an automated coding process. Second, we devise an interactive alignment algorithm for matching latent topics from multiple models, and enable sensitivity evaluation across a large number of models. Finally, we demonstrate that our tool enables social scientists to gain novel insights into three active research questions.


87: Extractive Summarisation Based on Keyword Profile and Language Model, by Han Xu, Eric Martin, Ashesh Mahidadia

We present a statistical framework to extract information-rich citation sentences that summarise the main contributions of a scientific paper. In a first stage, we automatically discover salient keywords from a paper's citation summary, keywords that characterise its main contributions. In a second stage, exploiting the results of the first stage, we identify citation sentences that best capture the paper's main contributions. Experimental results show that our approach using methods rooted in quantitative statistics and information theory outperforms the current state-of-the-art systems in scientific paper summarisation.

356: Combining Language and Vision with a Multimodal Skip-gram Model, by Angeliki Lazaridou, Nghia The Pham, Marco Baroni

We extend the SKIP-GRAM model of Mikolov et al. (2013a) by taking visual information into account. Like SKIP-GRAM, our multimodal models (MMSKIP-GRAM) build vector-based word representations by learning to predict linguistic contexts in text corpora. However, for a restricted set of words, the models are also exposed to visual representations of the objects they denote (extracted from natural images), and must predict linguistic and visual features jointly. The MMSKIP-GRAM models achieve good performance on a variety of semantic benchmarks. Moreover, since they propagate visual information to all words, we use them to improve image labeling and retrieval in the zero-shot setup, where the test concepts are never seen during model training. Finally, the MMSKIP-GRAM models discover intriguing visual properties of abstract words, paving the way to realistic implementations of embodied theories of meaning.

524: Inferring latent attributes of Twitter users with label regularization, by Ehsan Mohammady Ardehaly and Aron Culotta

Inferring latent attributes of online users has many applications in public health, politics, and marketing. Most existing approaches rely on supervised learning algorithms, which require manual data annotation and therefore are costly to develop and adapt over time. In this paper, we propose a lightly supervised approach based on label regularization to infer the age, ethnicity, and political orientation of Twitter users. Our approach learns from a heterogeneous collection of soft constraints derived from Census demographics, trends in baby names, and Twitter accounts that are emblematic of class labels. To counteract the imprecision of such constraints, we compare several constraint selection algorithms that optimize classification accuracy on a tuning set. We find that using no user-annotated data, our approach is within 2% of a fully supervised baseline for three of four tasks. Using a small set of labeled data for tuning further improves accuracy on all tasks.


278: HEADS: Headline Generation as Sequence Prediction Using an Abstract Feature-Rich Space, by Carlos A. Colmenares, Marina Litvak, Amin Mantrach, Fabrizio Silvestri

Automatic headline generation is a sub-task of document summarization with many reported applications. In this study we present a sequence-prediction technique for learning how editors title their news stories. The introduced technique models the problem as a discrete optimization task in a feature-rich space. In this space the global optimum can be found in polynomial time by means of dynamic programming. We train and test our model on an extensive corpus of financial news, and compare it against a number of baselines by using standard metrics from the document summarization domain, as well as some new ones proposed in this work. We also assess the readability and informativeness of the generated titles through human evaluation. The obtained results are very appealing and substantiate the soundness of the approach.

420: Discriminative Unsupervised Alignment of Natural Language Instructions with Corresponding Video Segments, by Iftekhar Naim, Young C. Song, Qiguang Liu, Liang Huang, Henry Kautz, Jiebo Luo, Daniel Gildea

We address the problem of automatically aligning natural language sentences with corresponding video segments without any direct supervision. Most existing algorithms for integrating language with videos rely on hand-aligned parallel data, where each natural language sentence is manually aligned with its corresponding image or video segment. Recently, fully unsupervised alignment of text with video has been shown to be feasible using hierarchical generative models. In contrast to the previous generative models, we propose three latent-variable discriminative models for the unsupervised alignment task. The proposed discriminative models are capable of incorporating domain knowledge, by adding diverse and overlapping features. The results show that discriminative models outperform the generative models in terms of alignment accuracy.

575: A Neural Network Approach to Context-Sensitive Generation of Conversational Responses, by Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, Bill Dolan

We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances. Our dynamic-context generative models show consistent gains over both context-sensitive and non-context-sensitive Machine Translation and Information Retrieval baselines.


3A: Generation and Summarization (Short Papers) — Plaza Ballroom A & B

Chair: Fei Liu, Carnegie Mellon University

3B: Information Extraction and Question Answering (Short Papers) — Plaza Ballroom D & E

Chair: Yejin Choi, University of Washington

3C: Machine Learning for NLP (Short Papers) — Plaza Ballroom F

Chair: Tong Zhang, Rutgers University


32: How to Make a Frenemy: Multitape FSTs for Portmanteau Generation, by Aliya Deri and Kevin Knight

A portmanteau is a type of compound word that fuses the sounds and meanings of two component words; for example, “frenemy” (friend + enemy) or “smog” (smoke + fog). We develop a system, including a novel multitape FST, that takes an input of two words and outputs possible portmanteaux. Our system is trained on a list of known portmanteaux and their component words, and achieves 45% exact matches in cross-validated experiments.

664: Entity Linking for Spoken Language, by Adrian Benton and Mark Dredze

Research on entity linking has considered a broad range of text, including newswire, blogs and web documents in multiple languages. However, the problem of entity linking for spoken language remains unexplored. Spoken language obtained from automatic speech recognition systems poses different types of challenges for entity linking; transcription errors can distort the context, and named entities tend to have high error rates. We propose features to mitigate these errors and evaluate the impact of ASR errors on entity linking using a new corpus of entity linked broadcast news transcripts.

227: When and why are log-linear models self-normalizing?, by Jacob Andreas and Dan Klein

Several techniques have recently been pro- posed for training “self-normalized” discriminative models. These attempt to find parameter settings for which unnormalized model scores approximate the true label probability. However, the theoretical properties of such techniques (and of self-normalization generally) have not been investigated. This paper examines the conditions under which we can expect self-normalization to work. We characterize a general class of distributions that admit self-normalization, and prove generalization bounds for procedures that minimize empirical normalizer variance. Motivated by these results, we describe a novel variant of an established procedure for training self-normalized models. The new procedure avoids computing normalizers for most training examples, and decreases training time by as much as factor of ten while preserving model quality.


477: Aligning Sentences from Standard Wikipedia to Simple Wikipedia, by William Hwang, Hannaneh Hajishirzi, Mari Ostendorf, Wei Wu

This work improves monolingual sentence alignment for text simplification, specifically for text in standard and simple Wikipedia. We introduce a method that improves over past efforts by using a greedy (vs. ordered) search over the document and a word-level se- mantic similarity score based on Wiktionary (vs. WordNet) that also accounts for structural similarity through syntactic dependencies. Experiments show improved performance on a hand-aligned set, with the largest gain coming from structural similarity. Resulting datasets of manually and automatically aligned sentence pairs are made available.

446: Spinning Straw into Gold: Using Free Text to Train Monolingual Alignment Models for Non-factoid Question Answering, by Rebecca Sharp, Peter Jansen, Mihai Surdeanu, Peter Clark

Monolingual alignment models have been shown to boost the performance of question answering systems by "bridging the lexical chasm" between questions and answers. The main limitation of these approaches is that they require semistructured training data in the form of question-answer pairs, which is difficult to obtain in specialized domains or low-resource languages. We propose two inexpensive methods for training alignment models solely using free text, by generating artificial question-answer pairs from discourse structures. Our approach is driven by two representations of discourse: a shallow sequential representation, and a deep one based on Rhetorical Structure Theory. We evaluate the proposed model on two corpora from different genres and domains: one from Yahoo! Answers and one from the biology domain, and two types of non-factoid questions: manner and reason. We show that these alignment models trained directly from discourse structures imposed on free text improve performance considerably over an information retrieval baseline and a neural network language model trained on the same data.

631: Deep Multilingual Correlation for Improved Word Embeddings, by Ang Lu, Weiran Wang, Mohit Bansal, Kevin Gimpel, Karen Livescu

Word embeddings have been found useful for many NLP tasks, including part-of-speech tagging, named entity recognition, and parsing. Adding multilingual context when learning embeddings can improve their quality, for example via canonical correlation analysis (CCA) on embeddings fromtwo languages. In this paper, we extend this idea to learn deep non-linear transformations of word embeddings of the two languages, using the recently proposed deep canonical correlation analysis. The resulting embeddings, when evaluated on multiple word and bigram similarity tasks, consistently improve over monolingual embeddings and over embeddings transformed with linear CCA.


570: Inducing Lexical Style Properties for Paraphrase and Genre Differentiation, by Ellie Pavlick and Ani Nenkova

We present an intuitive and effective method for inducing style scores on words and phrases. We exploit signal in a phrase’s rate of occurrence across stylistically contrasting corpora, making our method simple to implement and efficient to scale. We show strong results both intrinsically, by correlation with human judgements, and extrinsically, in applications to genre analysis and paraphrasing.

674: Personalized Page Rank for Named Entity Disambiguation, by Maria Pershina, Yifan He, Ralph Grishman

The task of Named Entity Disambiguation is to map entity mentions in the document to their correct entries in some knowledge base. We present a novel graph-based disambiguation approach based on Personalized PageRank (PPR) that combines local and global evidence for disambiguation and effectively filters out noise introduced by in- correct candidates. Experiments show that our method outperforms state-of-the-art ap- proaches by achieving 91.7% in micro- and 89.9% in macroaccuracy on a dataset of 27.8K named entity mentions.

689: Disfluency Detection with a Semi-Markov Model and Prosodic Features, by James Ferguson, Greg Durrett, Dan Klein

We present a discriminative model for detecting disfluencies in spoken language transcripts. Structurally, our model is a semi-Markov conditional random field with features targeting characteristics unique to speech repairs. This gives a significant performance improvement over standard chain-structured CRFs that have been employed in past work. We then incorporate prosodic features over silences and relative word duration into our semi-CRF model, resulting in further performance gains; moreover, these features are not easily replaced by discrete prosodic indicators such as ToBI breaks. Our final system, the semi-CRF with prosodic information, achieves an F-score of 85.4, which is 1.3 F1 better than the best prior reported F-score on this dataset.




One minute madness (Long + TACL papers) — Plaza Ballroom A, B & C

Chair: Joel Tetreault, Yahoo Labs


Poster session 1A: Long + TACL papers — Plaza Exhibits All

Slides: PDF


69: Robust Morphological Tagging with Word Representations, by Thomas Müller and Hinrich Schuetze

We present a comparative investigation of word representations for part-of-speech and morphological tagging, focusing on scenarios with considerable differences between training and test data where a robust approach is necessary. Instead of adapting the model towards a specific domain we aim to build a robust model across domains. We developed a test suite for robust tagging consisting of six languages and different domains. We find that representations similar to Brown clusters perform best for POS tagging and that word representations based on linguistic morphological analyzers perform best for morphological tagging.

123: Multiview LSA: Representation Learning via Generalized CCA, by Pushpendre Rastogi, Benjamin Van Durme, Raman Arora

Multiview LSA (MVLSA) is a generalization of Latent Semantic Analysis (LSA) that supports the fusion of arbitrary views of data and relies on Generalized Canonical Correlation Analysis (GCCA). We present an algorithm for fast approximate computation of GCCA, which when coupled with methods for handling missing values, is general enough to approximate some recent algorithms for inducing vector representations of words. Experiments across a comprehensive collection of test-sets show our approach to be competitive with the state of the art.

125: Incrementally Tracking Reference in Human/Human Dialogue Using Linguistic and Extra-Linguistic Information, by Casey Kennington, Ryu Iida, Takenobu Tokunaga, David Schlangen

A large part of human communication involves referring to entities in the world and often these entities are objects that are visually present for the interlocutors. A system that aims to resolve such references needs to tackle a complex task: objects and their visual features need to be determined, the referring expressions must be recognised, and extra-linguistic information such as eye gaze or pointing gestures need to be incorporated. Systems that can make use of such information sources exist, but have so far only been tested under very constrained settings, such as WOz interactions. In this paper, we apply to a more complex domain a reference resolution model that works incrementally (i.e., word by word), grounds words with visually present properties of objects (such as shape and size), and can incorporate extra-linguistic information. We find that the model works well compared to previous work on the same data, despite using fewer features. We conclude that the model shows potential for use in a real-time interactive dialogue system.

167: Digital Leafleting: Extracting Structured Data from Multimedia Online Flyers, by Emilia Apostolova, Payam Pourashraf, Jeffrey Sack

Marketing materials such as flyers and other infographics are a vast online resource. In a number of industries, such as the commercial real estate industry, they are in fact the only authoritative source of information. Companies attempting to organize commercial real estate inventories spend a significant amount of resources on manual data entry of this information. In this work, we propose a method for extracting structured data from free-form commercial real estate flyers in PDF and HTML formats. We modeled the problem as text categorization and Named Entity Recognition (NER) tasks and applied a supervised machine learning approach (Support Vector Machines). Our dataset consists of more than 2,200 commercial real estate flyers and associated manually entered structured data, which was used to automatically create training datasets. Traditionally, text categorization and NER approaches are based on textual information only. However, information in visually rich formats such as PDF and HTML is often conveyed by a combination of textual and visual features. Large fonts, visually salient colors, and positioning often indicate the most relevant pieces of information. We applied novel features based on visual characteristics in addition to traditional text features and show that performance improved significantly for both the text categorization and NER tasks.

169: Towards a standard evaluation method for grammatical error detection and correction, by Mariano Felice and Ted Briscoe

We present a novel evaluation method for grammatical error correction that addresses problems with previous approaches and scores systems in terms of improvement on the original text. Our method evaluates corrections at the token level using a globally optimal alignment between the source, a system hypothesis and a reference. Unlike the M2 Scorer, our method provides scores for both detection and correction and is sensitive to different types of edit operations.

205: Constraint-Based Models of Lexical Borrowing, by Yulia Tsvetkov, Waleed Ammar, Chris Dyer

Linguistic borrowing is the phenomenon of transferring linguistic constructions (lexical, phonological, morphological, and syntactic) from a “donor” language to a “recipient” language as a result of contacts between communities speaking different languages. Borrowed words are found in all languages, and—in contrast to cognate relationships—borrowing relationships may exist across unrelated languages (for example, about 40% of Swahili’s vocabulary is borrowed from Arabic). In this paper, we develop a model of morpho-phonological transformations across languages with features based on universal constraints from Optimality Theory (OT). Compared to several standard—but linguistically naïve—baselines, our OT-inspired model obtains good performance with only a few dozen training examples, making this a cost-effective strategy for sharing lexical information across languages.

229: Jointly Modeling Inter-Slot Relations by Random Walk on Knowledge Graphs for Unsupervised Spoken Language Understanding, by Yun-Nung Chen, William Yang Wang, Alexander Rudnicky

A key challenge of designing coherent semantic ontology for spoken language understanding is to consider inter-slot relations. In practice, however, it is difficult for domain experts and professional annotators to define a coherent slot set, while considering various lexical, syntactic, and semantic dependencies. In this paper, we exploit the typed syntactic dependency theory for unsupervised induction and filling of semantics slots in spoken dialogue systems. More specifically, we build two knowledge graphs: a slot-based semantic graph, and a word-based lexical graph. To jointly consider word-to-word, word-to-slot, and slot-to-slot relations, we use a random walk inference algorithm to combine the two knowledge graphs, guided by dependency grammars. The experiments show that considering inter-slot relations is crucial for generating a more coherent and compete slot set, resulting in a better spoken language understanding model, while enhancing the interpretability of semantic slots.

243: Expanding Paraphrase Lexicons by Exploiting Lexical Variants, by Atsushi Fujita and Pierre Isabelle

This study tackles the problem of paraphrase acquisition: achieving high coverage as well as accuracy. Our method first induces paraphrase patterns from given seed paraphrases, exploiting the generality of paraphrases exhibited by pairs of lexical variants, e.g., ``amendment'' and ``amending,'' in a fully empirical way. It then searches monolingual corpora for new paraphrases that match the patterns. This can extract paraphrases comprising words that are completely different from those of the given seeds. In experiments, our method expanded seed sets by factors of 42 to 206, gaining 84% to 208% more coverage than a previous method that generalizes only identical word forms. Human evaluation through a paraphrase substitution test demonstrated that the newly acquired paraphrases retained reasonable quality, given substantially high-quality seeds.

263: Lexicon-Free Conversational Speech Recognition with Neural Networks, by Andrew Maas, Ziang Xie, Dan Jurafsky, Andrew Ng

We present an approach to speech recognition that uses only a neural network to map acoustic input to characters, a character-level language model, and a beam search decoding procedure. This approach eliminates much of the complex infrastructure of modern speech recognition systems, making it possible to directly train a speech recognizer using errors generated by spoken language understanding tasks. The system naturally handles out of vocabulary words and spoken word fragments. We demonstrate our approach using the challenging Switchboard telephone conversation transcription task, achieving a word error rate competitive with existing baseline systems. To our knowledge, this is the first entirely neural-network-based system to achieve strong speech transcription results on a conversational speech task. We analyze qualitative differences between transcriptions produced by our lexicon-free approach and transcriptions produced by a standard speech recognition system. Finally, we evaluate the impact of large context neural network character language models as compared to standard n-gram models within our framework.

315: A Linear-Time Transition System for Crossing Interval Trees, by Emily Pitler and Ryan McDonald

We define a restricted class of non-projective trees that 1) covers many natural language sentences; and 2) can be parsed exactly with a generalization of the popular arc-eager system for projective trees (Nivre, 2003). Crucially, this generalization only adds constant overhead in run-time and space keeping the parser’s total run-time linear in the worst case. In empirical experiments, our proposed transition-based parser is more accurate on average than both the arc-eager system or the swap-based system, an unconstrained non-projective transition system with a worst-case quadratic runtime (Nivre, 2009).

367: Data-driven sentence generation with non-isomorphic trees, by Miguel Ballesteros, Bernd Bohnet, Simon Mille, Leo Wanner

Abstract structures from which the generation naturally starts often do not contain any functional nodes, while surface-syntactic structures or a chain of tokens in a linearized tree contain all of them. Therefore, data-driven linguistic generation needs to be able to cope with the projection between non-isomorphic structures that differ in their topology and number of nodes. So far, such a projection has been a challenge in data-driven generation and was largely avoided. We present a fully stochastic generator that is able to cope with projection between non-isomorphic structures. The generator, which starts from PropBank-like structures, consists of a cascade of SVM-classifier based submodules that map in a series of transitions the input structures onto sentences. The generator has been evaluated for English on the Penn-Treebank and for Spanish on the multi-layered Ancora-UPF corpus.

379: Ontologically Grounded Multi-sense Representation Learning for Semantic Vector Space Models, by Sujay Kumar Jauhar, Chris Dyer, Eduard Hovy

Words are polysemous. However, most approaches to representation learning for lexical semantics assign a single vector to every surface word type. Meanwhile, lexical ontologies such as WordNet provide a source of complementary knowledge to distributional information, including a word sense inventory. In this paper we propose two novel and general approaches for generating sense-specific word embeddings that are grounded in an ontology. The first applies graph smoothing as a post-processing step to tease the vectors of different senses apart, and is applicable to any vector space model. The second adapts predictive maximum likelihood models that learn word embeddings with latent variables representing senses grounded in an specified ontology. Empirical results on lexical semantic tasks show that our approaches effectively captures information from both the ontology and distributional statistics. Moreover, in most cases our sense-specific models outperform other models we compare against.

421: Subsentential Sentiment on a Shoestring: A Crosslingual Analysis of Compositional Classification, by Michael Haas and Yannick Versley

Sentiment analysis has undergone a shift from document-level analysis, where labels express the sentiment of a whole document or whole sentence, to subsentential approaches, which assess the contribution of individual phrases, in particular including the composition of sentiment terms and phrases such as negators and intensifiers. Starting from a small sentiment treebank modeled after the Stanford Sentiment Treebank of Socher et al. (2013), we investigate suitable methods to perform compositional sentiment classification for German in a data-scarce setting, harnessing cross-lingual methods as well as existing general-domain lexical resources.

497: Using Summarization to Discover Argument Facets in Online Idealogical Dialog, by Amita Misra, Pranav Anand, Jean E. Fox Tree, Marilyn Walker

More and more of the information available on the web is dialogic, and a significant portion of it takes place in online forum conversations about current social and political topics. We aim to develop tools to summarize what these conversations are about. What are the CENTRAL PROPOSITIONS associated with different stances on an issue; what are the abstract objects under discussion that are central to a speaker’s argument? How can we recognize that two CENTRAL PROPOSITIONS realize the same FACET of the argument? We hypothesize that the CENTRAL PROPOSITIONS are exactly those arguments that people find most salient, and use human summarization as a probe for discovering them. We describe our corpus of human summaries of opinionated dialogs, then show how we can identify similar repeated arguments, and group them into FACETS across many discussions of a topic. We define a new task, ARGUMENT FACET SIMILARITY (AFS), and show that we can predict AFS with a .54 correlation score, versus an ngram system baseline of .39 and a semantic textual similarity system baseline of .45.

521: Incorporating Word Correlation Knowledge into Topic Modeling, by Pengtao Xie, Diyi Yang, Eric Xing

This paper studies how to incorporate the external word correlation knowledge to improve the coherence of topic modeling. Existing topic models assume words are generated independently and lack the mechanism to utilize the rich similarity relationships among words to learn coherent topics. To solve this problem, we build a Markov Random Field (MRF) regularized Latent Dirichlet Allocation (LDA) model, which define a MRF on the latent topic layer of LDA to encourage words labeled as similar to share the same topic label. Under our model, the topic assignment of each word is not independent, but rather affected by the topic labels of its correlated words. Similar words have better chance to be put into the same topic due to the regularization of MRF, hence the coherence of topics can be boosted. In addition, our model can accommodate the subtlety that whether two words are similar depends on which topic they appear in, which allows word with multiple senses to be put into different topics properly. We derive a variational inference method to infer the posterior probabilities and learn model parameters and present techniques to deal with the hard-to-compute partition function in MRF. Experiments on two datasets demonstrate the effectiveness of our model.

525: Active Learning with Rationales for Text Classification, by Manali Sharma, Di Zhuang, Mustafa Bilgic

We present a simple and yet effective approach that can incorporate rationales elicited from annotators into the training of any off-the-shelf classifier. We show that our simple approach is effective for multinomial naive Bayes, logistic regression, and support vector machines. We additionally present an active learning method tailored specifically for the learning with rationales framework.

529: The Unreasonable Effectiveness of Word Representations for Twitter Named Entity Recognition, by Colin Cherry and Hongyu Guo

Named entity recognition (NER) systems trained on newswire perform very badly when tested on Twitter. Signals that were reliable in copy-edited text disappear almost entirely in Twitter's informal chatter, requiring the construction of specialized models. Using well-understood techniques, we set out to improve Twitter NER performance when given a small set of annotated training tweets. To leverage unlabeled tweets, we build Brown clusters and word vectors, enabling generalizations across distributionally similar words. To leverage annotated newswire data, we employ an importance weighting scheme. Taken all together, we establish a new state-of-the-art on two common test sets. Though it is well-known that word representations are useful for NER, supporting experiments have thus far focused on newswire data. We emphasize the effectiveness of representations on Twitter NER, and demonstrate that their inclusion can improve performance by up to 20 F1.

531: Inferring Temporally-Anchored Spatial Knowledge from Semantic Roles, by Eduardo Blanco and Alakananda Vempala

This paper presents a framework to infer spatial knowledge from verbal semantic role representations. First, we generate potential spatial knowledge deterministically. Second, we determine whether it can be inferred and a degree of certainty. Inferences capture that something is located or is not located somewhere, and temporally anchor this information. An annotation effort shows that inferences are ubiquitous and intuitive to humans.

541: Is Your Anchor Going Up or Down? Fast and Accurate Supervised Topic Models, by Thang Nguyen, Jordan Boyd-Graber, Jeffrey Lund, Kevin Seppi, Eric Ringger

Topic models provide insights into document collections, and their supervised extensions also capture associated document level metadata such as sentiment. However, inferring such models from data is often slow and cannot scale to big data. We build upon the ``anchor'' method for learning topic models to capture the relationship between metadata and latent topics by extending the vector space representation of word cooccurrence to include metadata specific dimensions. These additional dimensions reveal new anchor words that reflect specific combinations of metadata and topic. We show that these new latent representations predict sentiment as accurately as supervised topic models, and we find these representations more quickly without sacrificing interpretability.

557: Grounded Semantic Parsing for Complex Knowledge Extraction, by Ankur P. Parikh, Hoifung Poon, Kristina Toutanova

Recently, there has been increasing interest in learning semantic parsers with indirect supervision, but existing work focuses almost exclusively on question answering. Separately, there have been active pursuits in leveraging databases for distant supervision in information extraction, yet such methods are often limited to binary relations and none can handle nested events. In this paper, we generalize distant supervision to complex knowledge extraction, by proposing the first approach to learn a semantic parser for extracting nested event structures without annotated examples, using only a database of such complex events and unannotated text. The key idea is to model the annotations as latent variables, and incorporate a prior that favors semantic parses containing known events. Experiments on the GENIA event extraction dataset show that our approach can learn from and extract complex biological pathway events. Moreover, when supplied with just five example words per event type, it becomes competitive even among supervised systems, outperforming 19 out of 24 teams that participated in the original shared task.

589: Using External Resources and Joint Learning for Bigram Weighting in ILP-Based Multi-Document Summarization, by Chen Li, Yang Liu, Lin Zhao

Some state-of-the-art summarization systems use integer linear programming (ILP) based methods that aim to maximize the important concepts covered in the summary. These concepts are often obtained by selecting bigrams from the documents. In this paper, we improve such bigram based ILP summarization methods from different aspects. First we use syntactic information to select more important bigrams. Second, to estimate the importance of the bigrams, in addition to the internal features based on the test documents (e.g., document frequency, bigram positions), we propose to extract features by leveraging multiple external resources (such as word embedding from additional corpus,Wikipedia, Dbpedia,Word-Net, SentiWordNet). The bigram weights are then trained discriminatively in a joint learning model that predicts the bigram weights and selects the summary sentences in the ILP framework at the same time. We demonstrate that our system consistently outperforms the prior ILP method on different TAC data sets, and performs competitively compared to other previously reported best results. We also conducted various analysis to show the contribution of different components.

591: Transforming Dependencies into Phrase Structures, by Lingpeng Kong, Alexander M. Rush, Noah A. Smith

We present a new algorithm for transforming dependency parse trees into phrase-structure parse trees. We cast the problem as struc- tured prediction and learn a statistical model. Our algorithm is faster than traditional phrase- structure parsing and achieves 90.4% English parsing accuracy and 82.4% Chinese parsing accuracy, near to the state of the art on both benchmarks.

595: Déjà Image-Captions: A Corpus of Expressive Descriptions in Repetition, by Jianfu Chen, Polina Kuznetsova, David Warren, Yejin Choi

We present a new approach to harvesting a large-scale, high quality image-caption corpus that makes a better use of already existing web data with no additional human efforts. The key idea is to focus on Déjà Image-Captions: naturally existing image descriptions that are repeated almost verbatim – by more than one individual for different images. The resulting corpus provides association structure between 4 million images with 180K unique captions, capturing a rich spectrum of everyday narratives including figurative and pragmatic language. Exploring the use of the new corpus, we also present new conceptual tasks of visually situated paraphrasing, creative image captioning, and creative visual paraphrasing.

605: Improving the Inference of Implicit Discourse Relations via Classifying Explicit Discourse Connectives, by Attapol Rutherford and Nianwen Xue

Discourse relation classification is an important component for automatic discourse parsing and natural language understanding. The performance bottleneck of a discourse parser comes from implicit discourse relations, whose discourse connectives are not overtly present. Explicit discourse connectives can potentially be exploited to collect more training data to collect more data and boost the performance. However, using them indiscriminately has been shown to hurt the performance because not all discourse connectives can be dropped arbitrarily. Based on this insight, we investigate the interaction between discourse connectives and the discourse relations and propose the criteria for selecting the discourse connectives that can be dropped independently of the context without changing the interpretation of the discourse. Extra training data collected only by the freely omissible connectives improve the performance of the system without additional features.

617: Inferring Missing Entity Type Instances for Knowledge Base Completion: New Dataset and Methods, by Arvind Neelakantan and Ming-Wei Chang

Most of previous work in knowledge base (KB) completion has focused on the problem of relation extraction. In this work, we focus on the task of inferring missing entity type instances in a KB, a fundamental task for KB competition yet receives little attention.

Due to the novelty of this task, we construct a large-scale dataset and design an automatic evaluation methodology. Our knowledge base completion method uses information within the existing KB and external information from Wikipedia. We show that individual methods trained with a global objective that considers unobserved cells from both the entity and the type side gives consistently higher quality predictions compared to baseline methods. We also perform manual evaluation on a small subset of the data to verify the effectiveness of our knowledge base completion methods and the correctness of our proposed automatic evaluation method.

697: Pragmatic Neural Language Modelling in Machine Translation, by Paul Baltescu and Phil Blunsom

This paper presents an in-depth investigation on integrating neural language models in translation systems. Scaling neural language models is a difficult task, but crucial for real-world applications. This paper evaluates the impact on end-to-end MT quality of both new and existing scaling techniques. We show when explicitly normalising neural models is necessary and what optimisation tricks one should use in such scenarios. We also focus on scalable training algorithms and investigate noise contrastive estimation and diagonal contexts as sources for further speed improvements. We explore the trade-offs between neural models and back-off n-gram models and find that neural models make strong candidates for natural language applications in memory constrained environments, yet still lag behind traditional models in raw translation quality. We conclude with a set of recommendations one should follow to build a scalable neural language model for MT.

699: English orthography is not "close to optimal", by Garrett Nicolai and Grzegorz Kondrak

In spite of the apparent irregularity of the English spelling system, Chomsky and Halle (1968) characterize it as “near optimal”. We investigate this assertion using computational techniques and resources. We design an algorithm to generate word spellings that maximize both phonemic transparency and morphological consistency. Experimental results demonstrate that the constructed system is much closer to optimality than the traditional English orthography.

701: Key Female Characters in Film Have More to Talk About Besides Men: Automating the Bechdel Test, by Apoorv Agarwal, Jiehan Zheng, Shruti Kamath, Sriramkumar Balasubramanian, Shirin Ann Dey

The Bechdel test is a sequence of three questions designed to assess the presence of women in movies. Many believe that because women are seldom represented in film as strong leaders and thinkers, viewers associate weaker stereotypes with women. In this paper, we present a computational approach to automate the task of finding whether a movie passes or fails the Bechdel test. This allows us to study the key differences in language use and in the importance of roles of women in movies that pass the test versus the movies that fail the test. Our experiments confirm that in movies that fail the test, women are in fact portrayed as less-central and less-important characters.

TACL-255: Dense Event Ordering with a Multi-Pass Architecture, by Nathanael Chambers, Taylor Cassidy, Bill McDowell, Steven Bethard

The past 10 years of event ordering research has focused on learning partial orderings over document events and time expressions. The most popular corpus, the TimeBank, contains a small subset of the possible ordering graph. Many evaluations follow suit by only testing certain pairs of events (e.g., only main verbs of neighboring sentences). This has led most research to focus on specific learners for partial labelings. This paper attempts to nudge the discussion from identifying some relations to all relations. We present new experiments on strongly connected event graphs that contain ∼10 times more relations per document than the TimeBank. We also describe a shift away from the single learner to a sieve-based architecture that naturally blends multiple learners into a precision-ranked cascade of sieves. Each sieve adds labels to the event graph one at a time, and earlier sieves inform later ones through transitive closure. This paper thus describes innovations in both approach and task. We experiment on the densest event graphs to date and show a 14% gain over state-of-the-art.

TACL-371: Unsupervised Discovery of Biographical Structure from Text, by David Bamman and Noah A. Smith

We present a method for discovering abstract event classes in biographies, based on a probabilistic latent-variable model. Taking as input timestamped text, we exploit latent correlations among events to learn a set of event classes (such as "Born", "Graduates high school", and "Becomes citizen"), along with the typical times in a person's life when those events occur. In a quantitative evaluation at the task of predicting a person's age for a given event, we find that our generative model outperforms a strong linear regression baseline, along with simpler variants of the model that ablate some features. The abstract event classes that we learn allow us to perform a large-scale analysis of 242,970 Wikipedia biographies. Though it is known that women are greatly underrepresented on Wikipedia -- not only as editors (Wikipedia, 2011) but also as subjects of articles (Reagle and Rhue, 2011) -- we find that there is a bias in their characterization as well, with biographies of women containing significantly more emphasis on events of marriage and divorce than biographies of men.

TACL-381: Locally Non-Linear Learning for Statistical Machine Translation via Discretization and Structured Regularization, by Jonathan H. Clark, Chris Dyer, Alon Lavie

Linear models, which support efficient learning and inference, are the workhorses of statistical machine translation; however, linear decision rules are less attractive from a modeling perspective. In this work, we introduce a technique for learning arbitrary, rule-local, nonlinear feature transforms that improve model expressivity, but do not sacrifice the efficient inference and learning associated with linear models. To demonstrate the value of our technique, we discard the customary log transform of lexical probabilities and drop the phrasal translation probability in favor of raw counts. We observe that our algorithm learns a variation of a log transform that leads to better translation quality compared to the explicit log transform. We conclude that non-linear responses play an important role in SMT, an observation that we hope will inform the efforts of feature engineers.

TACL-385: 2-Slave Dual Decomposition for Generalized High Order CRFs, by Xian Qian and Yang Liu

We show that the decoding problem in generalized Higher Order Conditional Random Fields (CRFs) can be decomposed into two parts: one is a tree labeling problem that can be solved in linear time using dynamic programming; the other is a supermodular quadratic pseudo-Boolean maximization problem, which can be solved in cubic time using a minimum cut algorithm. We use dual decomposition to force their agreement. Experimental results on Twitter named entity recognition and sentence dependency tagging tasks show that our method outperforms spanning tree based dual decomposition

TACL-403: SPRITE: Generalizing Topic Models with Structured Priors, by Michael J. Paul, Mark Dredze

We introduce SPRITE, a family of topic models that incorporates structure into model priors as a function of underlying components. The structured priors can be constrained to model topic hierarchies, factorizations, correlations, and supervision, allowing SPRITE to be tailored to particular settings. We demonstrate this flexibility by constructing a SPRITE-based model to jointly infer topic hierarchies and author perspective, which we apply to corpora of political debates and online reviews. We show that the model learns intuitive topics, outperforming several other topic models at predictive tasks.

TACL-429: Learning Strictly Local Subsequential Functions, by Jane Chandlee, Remi Eyraud, Jeffrey Heinz

We define two proper subclasses of subsequential functions based on the concept of Strict Locality (McNaughton and Papert, 1971; Rogers and Pullum, 2011; Rogers et al., 2013) for formal languages. They are called Input and Output Strictly Local (ISL and OSL). We provide an automata-theoretic characterization of the ISL class and theorems establishing how the classes are related to each other and to Strictly Local languages. We give evidence that local phonological and morphological processes belong to these classes. Finally we provide a learning algorithm which provably identifies the class of ISL functions in the limit from positive data in polynomial time and data. We demonstrate this learning result on appropriately synthesized artificial corpora. We leave a similar learning result for OSL functions for future work and suggest future directions for addressing non-local phonological processes.

TACL-485: A sense-topic model for WSI with unsupervised data enrichment, by Jing Wang, Mohit Bansal, Kevin Gimpel, Brian D. Ziebart, Clement T. Yu

Word sense induction (WSI) seeks to automatically discover the senses of a word in a corpus via unsupervised methods. We propose a sense-topic model for WSI, which treats sense and topic as two separate latent variables to be inferred jointly. Topics are informed by the entire document, while senses are informed by the local context surrounding the ambiguous word. We also discuss unsupervised ways of enriching the original corpus in order to improve model performance, including using neural word embeddings and external corpora to expand the context of each data instance. We demonstrate significant improvements over the previous state-of-the-art, achieving the best results reported to date on the SemEval-2013 WSI task.


Poster session 1B: Long + TACL papers — Plaza Exhibits All

Slides: PDF


56: Modeling Word Meaning in Context with Substitute Vectors, by Oren Melamud, Ido Dagan, Jacob Goldberger

Context representations are a key element in distributional models of word meaning. In contrast to typical representations based on neighboring words, a recently proposed approach suggests to represent a context of a target word by a substitute vector, comprising the potential fillers for the target word slot in that context. In this work we first propose a variant of substitute vectors, which we find particularly suitable for measuring context similarity. Then, we propose a novel model for representing word meaning in context based on this context representation. Our model outperforms state-of-the-art results on lexical substitution tasks in an unsupervised setting.

90: LCCT: A Semi-supervised Model for Sentiment Classification, by Min Yang, Wenting Tu, Ziyu Lu, Wenpeng Yin, Kam-Pui Chow

Analyzing public opinions towards products, services and social events is an important but challenging task. An accurate sentiment analyzer should take both lexicon-level information and corpus-level information into account. It also needs to exploit the domain-specific knowledge and utilize the common knowledge shared across domains. In addition, we want the algorithm being able to deal with missing labels and learning from incomplete sentiment lexicons. This paper presents a LCCT (Lexicon-based and Corpus-based, Co-Training) model for semi-supervised sentiment classification. The proposed method combines the idea of lexicon-based learning and corpus-based learning in a unified co-training framework. It is capable of incorporating both domain-specific and domain-independent knowledge. Extensive experiments show that it achieves very competitive classification accuracy, even with a small portion of labeled data. Comparing to state-of-the-art sentiment classification methods, the LCCT approach exhibits significantly better performances on a variety of datasets in both English and Chinese.

116: Empty Category Detection With Joint Context-Label Embeddings, by Xun Wang, Katsuhito Sudoh, Masaaki Nagata

This paper presents a novel technique for empty category (EC) detection using distributed word representations. We formulate it as an annotation task. We explore the hidden layer of a neural network by mapping both the distributed representations of the contexts of ECs and EC types to a low dimensional space. In the testing phase, using the model learned from annotated data, we project the context of a possible EC position to the same space and further compare it with the representations of EC types. The closet EC type is assigned to the candidate position. Experiments on Chinese Treebank prove the effectiveness of the proposed method. We improve the precision by about 6 point on a subset of Chinese Treebank, which is a new state-of-the-art performance on CTB.

150: NASARI: a Novel Approach to a Semantically-Aware Representation of Items, by José Camacho-Collados, Mohammad Taher Pilehvar, Roberto Navigli

The semantic representation of individual word senses and concepts is of fundamental importance to several applications in Natural Language Processing. To date, concept modeling techniques have in the main based their representation either on lexicographic resources, such as WordNet, or on encyclopedic resources, such as Wikipedia. We propose a vector representation technique that combines the complementary knowledge of both these types of resource. Thanks to its use of explicit semantics combined with a novel cluster-based dimensionality reduction and an effective weighting scheme, our representation attains state-of-the-art performance on multiple datasets in two standard benchmarks: word similarity and sense clustering. We are releasing our vector representations at

172: Multi-Target Machine Translation with Multi-Synchronous Context-free Grammars, by Graham Neubig, Philip Arthur, Kevin Duh

We propose a method for simultaneously translating from a single source language to multiple target languages T1, T2, etc. The motivation behind this method is that if we only have a weak language model for T1 and translations in T1 and T2 are associated, we can use the information from a strong language model over T2 to disambiguate the translations in T1, providing better translation results. As a specific framework to realize multi-target translation, we expand the formalism of synchronous context-free grammars to handle multiple targets, and describe methods for rule extraction, scoring, pruning, and search with these models. Experiments find that multi-target translation with a strong language model in a similar second target language can provide gains of up to 0.8-1.5 BLEU points.

178: Using Zero-Resource Spoken Term Discovery for Ranked Retrieval, by Jerome White, Douglas Oard, Aren Jansen, Jiaul Paik, Rashmi Sankepally

Research on ranked retrieval of spoken content has assumed the existence of some automated (word or phonetic) transcription. Recently, however, methods have been demonstrated for matching spoken terms to spoken content without the need for language-tuned transcription. This paper describes the first application of such techniques to ranked retrieval, evaluated using a newly created test collection. Both the queries and the collection to be searched are based on Gujarati produced naturally by native speakers; relevance assessment was performed by other native speakers of Gujarati. Ranked retrieval is based on fast acoustic matching that identifies a deeply nested set of matching speech regions, coupled with ways of combining evidence from those matching regions. Results indicate that the resulting ranked lists may be useful for some practical similarity-based ranking tasks.

196: Sign constraints on feature weights improve a joint model of word segmentation and phonology, by Mark Johnson, Joe Pater, Robert Staubs, Emmanuel Dupoux

This paper describes a joint model of word segmentation and phonological alternations, which takes unsegmented utterances as input and infers word segmentations and underlying phonological representations. The model is a Maximum Entropy or log-linear model, which can express a probabilistic version of Optimality Theory (OT; Prince 2004), a standard phonological framework. The features in our model are inspired by OT's Markedness and Faithfulness constraints. Following the OT principle that such features indicate ``violations'', we require their weights to be non-positive. We apply our model to a modified version of the Buckeye corpus (Pitt 2007) in which the only phonological alternations are deletions of word-final /d/ and /t/ segments. The model sets a new state-of-the-art for this corpus for word segmentation, identification of underlying forms, and identification of /d/ and /t/ deletions.

We also show that the OT-inspired sign constraints on feature weights are crucial for accurate identification of deleted /d/s; without them our model posits approximately 10 times more deleted underlying /d/s than appear in the manually annotated data.

218: Semi-Supervised Word Sense Disambiguation Using Word Embeddings in General and Specific Domains, by Kaveh Taghipour and Hwee Tou Ng

One of the weaknesses of current supervised word sense disambiguation (WSD) systems is that they only treat a word as a discrete entity. However, a continuous-space representation of words (word embeddings) can provide valuable information and thus improve generalization accuracy. Since word embeddings are typically obtained from unlabeled data using unsupervised methods, this method can be seen as a semi-supervised word sense disambiguation approach. This paper investigates two ways of incorporating word embeddings in a word sense disambiguation setting and evaluates these two methods on some SensEval/SemEval lexical sample and all-words tasks and also a domain-specific lexical sample task. The obtained results show that such representations consistently improve the accuracy of the selected supervised WSD system. Moreover, our experiments on a domain-specific dataset show that our supervised baseline system beats the best knowledge-based systems by a large margin.

222: Model Invertibility Regularization: Sequence Alignment With or Without Parallel Data, by Tomer Levinboim, Ashish Vaswani, David Chiang

We present Model Invertibility Regularization MIR, a method that jointly trains two directional sequence alignment models, one in each direction, and takes into account the invertibility of the alignment task.

By coupling the two models through their parameters (as opposed to through their inferences, as in Liang et al.'s Alignment by Agreement (\method{ABA}), and Ganchev et al.'s Posterior Regularization (\method{PostCAT})), our method seamlessly extends to all IBM-style word alignment models as well as to alignment without parallel data.

Our proposed algorithm is mathematically sound and inherits convergence guarantees from EM. We evaluate MIR on two tasks: (1) On word alignment, applying MIR on fertility based models we attain higher F-scores than ABA and PostCAT. (2) On Japanese-to-English back-transliteration without parallel data, applied to the decipherment model of Ravi and Knight, MIR learns sparser models that close the gap in whole-name error rate by 33% relative to a model trained on parallel data, and further, beats a previous approach by Mylonakis et al.

226: Continuous Space Representations of Linguistic Typology and their Application to Phylogenetic Inference, by Yugo Murawaki

For phylogenetic inference, linguistic typology is a promising alternative to lexical evidence because it allows us to compare an arbitrary pair of languages. A challenging problem with typology-based phylogenetic inference is that the changes of typological features over time are less intuitive than those of lexical features. In this paper, we work on reconstructing typologically natural ancestors To do this, we leverage dependencies among typological features. We first represent each language by continuous latent components that capture feature dependencies. We then combine them with a typology evaluator that distinguishes typologically natural languages from other possible combinations of features. We perform phylogenetic inference in the continuous space and use the evaluator to ensure the typological naturalness of inferred ancestors. We show that the proposed method reconstructs known language families more accurately than baseline methods. Lastly, assuming the monogenesis hypothesis, we attempt to reconstruct a common ancestor of the world's languages.

232: Interpreting Compound Noun Phrases Using Web Search Queries, by Marius Pasca

A weakly-supervised method is applied to anonymized queries to extract lexical interpretations of compound noun phrases (e.g., "fortune 500 companies"). The interpretations explain the subsuming role ("listed in") that modifiers ("fortune 500") play relative to heads ("companies") within the noun phrases. Experimental results over evaluation sets of noun phrases from multiple sources demonstrate that interpretations extracted from queries have encouraging coverage and precision. The top interpretation extracted is deemed relevant for more than 70% of the noun phrases.

274: Diamonds in the Rough: Event Extraction from Imperfect Microblog Data, by Ander Intxaurrondo, Eneko Agirre, Oier Lopez de Lacalle, Mihai Surdeanu

We introduce a distantly supervised event ex- traction approach that extracts complex event templates from microblogs. We show that this near real-time data source is more challeng- ing than news because it contains information that is both approximate (e.g., with values that are close but different from the gold truth) and ambiguous (due to the brevity of the texts), impacting both the evaluation and extraction methods. For the former, we propose a novel, “soft”, F1 metric that incorporates similarity between extracted fillers and the gold truth, giving partial credit to different but similar values. With respect to extraction method- ology, we propose two extensions to the dis- tant supervision paradigm: to address approx- imate information, we allow positive training examples to be generated from information that is similar but not identical to gold values; to address ambiguity, we aggregate contexts across tweets discussing the same event. We evaluate our contributions on the complex do- main of earthquakes, with events with up to 20 arguments. Our results indicate that, de- spite their simplicity, our contributions yield a statistically-significant improvement of 25% (relative) over a strong distantly-supervised system. The dataset containing the knowledge base, relevant tweets and manual annotations is publicly available.

296: I Can Has Cheezburger? A Nonparanormal Approach to Combining Textual and Visual Information for Predicting and Generating Popular Meme Descriptions, by William Yang Wang and Miaomiao Wen

The advent of social media has brought Internet memes, a unique social phenomenon, to the front stage of the Web. Embodied in the form of images with text descriptions, little do we know about the ``language of memes''. In this paper, we statistically study the correlations among popular memes and their wordings, and generate meme descriptions from raw images. To do this, we take a multimodal approach---we propose a robust nonparanormal model to learn the stochastic dependencies among the image, the candidate descriptions, and the popular votes. In experiments, we show that combining text and vision helps identifying popular meme descriptions; that our nonparanormal model is able to learn dense and continuous vision features jointly with sparse and discrete text features in a principled manner, outperforming various competitive baselines; that our system can generate meme descriptions using a simple pipeline.

298: Unsupervised Dependency Parsing: Let's Use Supervised Parsers, by Phong Le and Willem Zuidema

We present a self-training approach to unsupervised dependency parsing that reuses existing supervised and unsupervised parsing algorithms. Our approach, called `iterated reranking' (IR), starts with dependency trees generated by an unsupervised parser, and iteratively improves these trees using the richer probability models used in supervised parsing that are in turn trained on these trees. Our system achieves 1.8% accuracy higher than the state-of-the-part parser of Spitkovsky et al. (2013) on the WSJ corpus.

306: A Transition-based Algorithm for AMR Parsing, by Chuan Wang, Nianwen Xue, Sameer Pradhan

We present a two-stage framework to parse a sentence into its Abstract Meaning Representation (AMR). We first use a dependency parser to generate a dependency tree for the sentence. In the second stage, we design a novel transition-based algorithm that transforms the dependency tree to an AMR graph. There are several advantages with this approach. First, the dependency parser can be trained on a training set much larger than the training set for the tree-to-graph algorithm, resulting in a more accurate AMR parser overall. Our parser yields an improvement of 5% absolute in F-measure over the best previous result. Second, the actions that we design are linguistically intuitive and capture the regularities in the mapping between the dependency structure and the AMR of a sentence. Third, our parser runs in nearly linear time in practice in spite of a worst-case complexity of O(n2).

322: The Geometry of Statistical Machine Translation, by Aurelien Waite and Bill Byrne

Most modern statistical machine translation systems are based on linear statistical models. One extremely effective method for estimating the model parameters is minimum error rate training (MERT), which is an efficient form of line optimisation adapted to the highly non-linear objective functions used in machine translation. We describe a polynomial-time generalisation of line optimisation that computes the error surface over a plane embedded in parameter space. The description of this algorithm relies on convex geometry, which is the mathematics of polytopes and their faces.

Using this geometric representation of MERT we investigate whether the optimisation of linear models is tractable in general. Previous work on finding optimal solutions in MERT (Galley and Quirk, 2011) established a worst-case complexity that was exponential in the number of sentences, in contrast we show that exponential dependence in the worst-case complexity is mainly in the number of features.

Although our work is framed with respect to MERT, the convex geometric description is also applicable to other error-based training methods for linear models. We believe our analysis has important ramifications because it suggests that the current trend in building statistical machine translation systems by introducing a very large number of sparse features is inherently not robust.

336: Unsupervised Multi-Domain Adaptation with Feature Embeddings, by Yi Yang and Jacob Eisenstein

Representation learning is the dominant technique for unsupervised domain adaptation, but existing approaches have two major weaknesses. First, they often require the specification of ``pivot features'' that generalize across domains, which are selected by task-specific heuristics. We show that a novel but simple feature embedding approach provides better performance, by exploiting the feature template structure common in NLP problems. Second, unsupervised domain adaptation is typically treated as a task of moving from a single source to a single target domain. In reality, test data may be diverse, relating to the training data in some ways but not others. We propose an alternative formulation, in which each instance has a vector of domain attributes, can be used to learn distill the domain-invariant properties of each feature.

404: Latent Domain Word Alignment for Heterogeneous Corpora, by Hoang Cuong and Khalil Sima'an

This work focuses on the insensitivity of existing word alignment models to domain differences, which often yields suboptimal results on large heterogeneous data. A novel latent domain word alignment model is proposed, which induces domain-conditioned lexical and alignment statistics. We propose to train the model on a heterogeneous corpus under partial supervision, using a small number of seed samples from different domains. The seed samples allow estimating sharper, domain-conditioned word alignment statistics for sentence pairs. Our experiments show that the derived domain-conditioned statistics, once combined together, produce notable improvements both in word alignment accuracy and in translation accuracy of their resulting SMT systems.

428: Extracting Human Temporal Orientation from Facebook Language, by H. Andrew Schwartz, Gregory Park, Maarten Sap, Evan Weingarten, Johannes Eichstaedt, Margaret Kern, David Stillwell, Michal Kosinski, Jonah Berger, Martin Seligman, Lyle Ungar

People vary widely in their temporal orientation --- how often they emphasize the past, present, and future --- and this affects their finances, health, and happiness. Traditionally, temporal orientation has been assessed by self-report questionnaires. In this paper, we develop a novel behavior-based assessment using human language on Facebook. We first create a past, present, and future message classifier, engineering features and evaluating a variety of classification techniques. Our message classifier achieves an accuracy of 71.8%, compared with 52.8% from the most frequent class and 58.6% from a model based entirely on time expression features. We quantify a users’ overall temporal orientation based on their distribution of messages and validate it against known human correlates: conscientiousness, age, and gender. We then explore social scientific questions, finding novel associations with the factors openness to experience, satisfaction with life, depression, IQ, and one’s number of friends. Further, demonstrating how one can track orientation over time, we find differences in future orientation around birthdays.

438: Cost Optimization in Crowdsourcing Translation: Low cost translations made even cheaper, by Mingkun Gao, Wei Xu, Chris Callison-Burch

Crowdsourcing makes it possible to create translations at much lower cost than hiring professional translators. However, it is still expensive to obtain the millions of translations that are needed to train statistical machine translation systems. We propose two mechanisms to reduce the cost of crowdsourcing while maintaining high translation quality. First, we develop a method to reduce redundant translations. We train a linear model to evaluate the translation quality on a sentence-by-sentence basis, and fit a threshold between acceptable and unacceptable translations. Unlike past work, which always paid for a fixed number of translations for each source sentence and then chose the best from them, we can stop earlier and pay less when we receive a translation that is good enough. Second, we introduce a method to reduce the pool of translators by quickly identifying bad translators after they have translated only a few sentences. This also allows us to rank translators, so that we re-hire only good translators to reduce cost.

448: An In-depth Analysis of the Effect of Text Normalization in Social Media, by Tyler Baldwin and Yunyao Li

Recent years have seen increased interest in text normalization in social media, as the informal writing styles found in Twitter and other social media data often cause problems for NLP applications. Unfortunately, most current approaches narrowly regard the normalization task as a ``one size fits all'' task of replacing non-standard words with their standard counterparts. In this work we build a taxonomy of normalization edits and present a study of normalization to examine its effect on three different downstream applications (dependency parsing, named entity recognition, and text-to-speech synthesis). The results suggest that how the normalization task should be viewed is highly dependent on the targeted application. The results also show that normalization must be thought of as more than word replacement in order to produce results comparable to those seen on clean text.

460: Multitask Learning for Adaptive Quality Estimation of Automatically Transcribed Utterances, by José G. C. de Souza, Hamed Zamani, Matteo Negri, Marco Turchi, Falavigna Daniele

We investigate the problem of predicting the quality of automatic speech recognition (ASR) output under the following rigid constraints: i) reference transcriptions are not available, ii) confidence information about the system that produced the transcriptions is not accessible, and iii) training and test data come from multiple domains. To cope with these constraints (typical of the constantly increasing amount of automatic transcriptions that can be found on the Web), we propose a domain-adaptive approach based on multitask learning. Different algorithms and strategies are evaluated with English data coming from four domains, showing that the proposed approach can cope with the limitations of previously proposed single task learning methods.

552: A Dynamic Programming Algorithm for Tree Trimming-based Text Summarization, by Masaaki Nishino, Norihito Yasuda, Tsutomu Hirao, Shin-ichi Minato, Masaaki Nagata

Tree trimming is the problem of extracting an optimal subtree from an input tree, and sentence extraction and sentence compression methods can be formulated and solved as tree trimming problems. Previous approaches require integer linear programming (ILP) solvers to obtain exact solutions. The problem of this approach is that ILP solvers are black-boxes and have no theoretical guarantee as to their computation complexity. We propose a dynamic programming (DP) algorithm for tree trimming problems whose running time is O(NL log N), where N is the number of tree nodes and L is the length limit. Our algorithm exploits the zero-suppressed binary decision diagram (ZDD), a data structure that represents a family of sets as a directed acyclic graph, to represent the set of subtrees in a compact form; the structure of ZDD permits the application of DP to obtain exact solutions, and our algorithm is applicable to different tree trimming problems. Moreover, experiments show that our algorithm is faster than state-of-the-art ILP solvers, and that it scales well to handle large summarization problems.

578: Sentiment after Translation: A Case-Study on Arabic Social Media Posts, by Mohammad Salameh, Saif Mohammad, Svetlana Kiritchenko

When text is translated from one language into another, sentiment is preserved to varying degrees. In this paper, we use Arabic social media posts as stand-in for source language text, and determine loss in sentiment predictability when they are translated into English, manually and automatically. As benchmarks, we use manually and automatically determined sentiment labels of the Arabic texts. We show that sentiment analysis of English translations of Arabic texts produces competitive results, w.r.t. Arabic sentiment analysis. We discover that even though translation significantly reduces the human ability to recover sentiment, automatic sentiment systems are still able to capture sentiment information from the translations.

586: Corpus-based discovery of semantic intensity scales, by Chaitanya Shivade, Marie-Catherine de Marneffe, Eric Fosler-Lussier, Albert M. Lai

Gradable terms such as brief, lengthy and extended illustrate varying degrees of a scale and can therefore participate in comparative constructs. Knowing the set of words that can be compared on the same scale and the associated ordering between them (brief < lengthy < extended) is very useful for a variety of lexical semantic tasks. Current techniques to derive such an ordering rely on WordNet to determine which words belong on the same scale and are limited to adjectives. Here we describe an extension to recent work: we investigate a fully automated pipeline to extract gradable terms from a corpus, group them into clusters reflecting the same scale and establish an ordering among them. This methodology reduces the amount of required handcrafted knowledge, and can infer gradability of words independent of their part of speech. Our approach infers an ordering for adjectives with comparable performance to previous work, but also for adverbs with an accuracy of 71%. We find that the technique is useful for inferring such rankings among words across different domains, and present an example using biomedical text.

590: Dialogue focus tracking for zero pronoun resolution, by Sudha Rao, Allyson Ettinger, Hal Daumé III, Philip Resnik

We take a novel approach to zero pronoun resolution in Chinese: our model explicitly tracks the flow of focus in a discourse. Our approach, which generalizes to deictic references, is not reliant on the presence of overt noun phrase antecedents to resolve to, and allows us to address the large percentage of "non-anaphoric" pronouns filtered out in other approaches. We furthermore train our model using readily available parallel Chinese/English corpora, allowing for training without hand-annotated data. Our results demonstrate improvements on two test sets, as well as the usefulness of linguistically motivated features.

648: Solving Hard Coreference Problems, by Haoruo Peng, Daniel Khashabi, Dan Roth

Coreference resolution is a key problem in natural language understanding that still escapes reliable solutions. One fundamental difficulty has been that of resolving instances involving pronouns since they often require deep language understanding and use of background knowledge. In this paper we propose an algorithmic solution that involves a new representation for the knowledge required to address hard coreference problems, along with a constrained optimization framework that uses this knowledge in coreference decision making. Our representation, Predicate Schemas, is instantiated with knowledge acquired in an unsupervised way, and is compiled automatically into constraints that impact the coreference decision. We present a general coreference resolution system that significantly improves state-of-the-art performance on hard, Winograd-style, pronoun resolution cases, while still performing at the state-of-the-art level on standard coreference resolution datasets.

TACL-452: Reasoning about Quantities in Natural Language, by Subhro Roy, Tim Vieira, Dan Roth

Little work from the Natural Language Processing community has targeted the role of quantities in Natural Language Understanding. This paper takes some key steps towards facilitating reasoning about quantities expressed in natural language. We investigate two different tasks of numerical reasoning. First, we consider Quantity Entailment, a new task formulated to understand the role of quantities in general textual inference tasks. Second, we consider the problem of automatically understanding and solving elementary school math word problems. In order to address these quantitative reasoning problems we first develop a computational approach which we show to successfully recognize and normalize textual expressions of quantities. We then use these capabilities to further develop algorithms to assist reasoning in the context

TACL-472: Learning Constraints for Information Structure Analysis of Scientific Documents, by Yufan Guo, Roi Reichart, Anna Korhonen

Inferring the information structure of scientific documents is useful for many NLP applications. Existing approaches to this task require substantial human effort. We propose a framework for constraint learning that reduces human involvement considerably. Our model uses topic models to identify latent topics and their key linguistic features in input documents, induces constraints from this information and maps sentences to their dominant information structure categories through a constrained unsupervised model. When the induced constraints are combined with a fully unsupervised model, the resulting model challenges existing lightly supervised feature-based models as well as unsupervised models that use manually constructed declarative knowledge. Our results demonstrate that useful declarative knowledge can be learned from data with very limited human involvement.

Tuesday, June 2


Registration and Breakfast


4A: Dialogue and Spoken Language Processing (Long Papers) — Plaza Ballroom A & B

Chair: Marilyn Walker, University of California, Santa Cruz

4B: Machine Learning for NLP (Long Papers) — Plaza Ballroom D & E

Chair: Amarnag Subramanya, Google Research

4C: Phonology, Morphology and Word Segmentation (Long Papers) — Plaza Ballroom F

Chair: Hal Daume III, University of Maryland


490: Semantic Grounding in Dialogue for Complex Problem Solving, by Xiaolong Li and Kristy Boyer

Dialogue systems that support users in complex problem solving must interpret user utterances within the context of a dynamically changing, user-created problem solving artifact. This paper presents a novel approach to semantic grounding of noun phrases within tutorial dialogue for computer programming. Our approach performs joint segmentation and labeling of the noun phrases to link them to attributes of entities within the problem-solving environment. Evaluation results on a corpus of tutorial dialogue for Java programming demonstrate that a Conditional Random Field model performs well, achieving an accuracy of 89.3% for linking semantic segments to the correct entity attributes. This work is a step toward enabling dialogue systems to support users in increasingly complex problem-solving tasks.

288: Early Gains Matter: A Case for Preferring Generative over Discriminative Crowdsourcing Models, by Paul Felt, Kevin Black, Eric Ringger, Kevin Seppi, Robbie Haertel

In modern practice, labeling a dataset often involves aggregating annotator judgments obtained from crowdsourcing. State-of-the-art aggregation is performed via inference on probabilistic models, some of which are data-aware, meaning that they leverage features of the data (e.g., words in a document) in addition to annotator judgments. Previous work largely prefers discriminatively trained conditional models. This paper demonstrates that a data-aware crowdsourcing model incorporating a generative multinomial data model enjoys a strong competitive advantage over its discriminative log-linear counterpart in the typical crowdsourcing setting. That is, the generative approach is better except when the annotators are highly accurate in which case simple majority vote is often sufficient. Additionally, we present a novel mean-field variational inference algorithm for the generative model that significantly improves on the previously reported state-of-the-art for that model. We validate our conclusions on six text classification datasets with both human-generated and synthetic annotations.

688: Inflection Generation as Discriminative String Transduction, by Garrett Nicolai, Colin Cherry, Grzegorz Kondrak

We approach the task of morphological inflection generation as discriminative string transduction. Our supervised system learns to generate word-forms from lemmas accompanied by morphological tags, and refines them by referring to the other forms within a paradigm. Results of experiments on six diverse languages with varying amounts of training data demonstrate that our approach improves the state of the art in terms of predicting inflected word-forms.


661: Learning Knowledge Graphs for Question Answering through Conversational Dialog, by Ben Hixon, Peter Clark, Hannaneh Hajishirzi

We describe how a question-answering system can learn about its domain from conversational dialogs. Our system learns to relate concepts in science questions to propositions in a fact corpus, stores new concepts and relations in a knowledge graph (KG), and uses the graph to solve questions. We are the first to acquire knowledge for question-answering from open, natural language dialogs without a fixed ontology or domain model that predetermines what users can say. Our relation-based strategies complete more successful dialogs than a query expansion baseline, our task-driven relations are more effective for solving science questions than relations from general knowledge sources, and our method is practical enough to generalize to other domains.

407: Optimizing Multivariate Performance Measures for Learning Relation Extraction Models, by Gholamreza Haffari, Ajay Nagesh, Ganesh Ramakrishnan

We describe a novel max-margin learning approach to optimize non-linear performance measures for distantly-supervised relation extraction models. Our approach can be generally used to learn latent variable models under multivariate non-linear performance measures, such as F_β-score. Our approach interleaves Concave-Convex Procedure (CCCP) for populating latent variables with dual decomposition to factorize the original hard problem into smaller independent sub-problems. The experimental results demonstrate that our learning algorithm is more effective than the ones commonly used in the literature for distant supervision of information extraction models. On several data conditions, we show that our method outperforms the baseline and results in up to 8.5% improvement in the F_1-score.

452: Penalized Expectation Propagation for Graphical Models over Strings, by Ryan Cotterell and Jason Eisner

We present penalized expectation propagation, a novel algorithm for approximate inference in graphical models. Expectation propagation is a variant of loopy belief propagation that keeps messages tractable by projecting them back into a given family of functions. Our extension speeds up the method by using a structured-sparsity penalty to prefer simpler messages within the family. In the case of string-valued random variables, penalized EP lets us work with an expressive non-parametric function family based on variable-length n-gram models. On phonological inference problems, we obtain substantial speedup over previous related algorithms with no significant loss in accuracy.


82: Sentence segmentation of aphasic speech, by Kathleen C. Fraser, Naama Ben-David, Graeme Hirst, Naida Graham, Elizabeth Rochon

Automatic analysis of impaired speech for screening or diagnosis is a growing research field; however there are still many barriers to a fully automated approach. When automatic speech recognition is used to obtain the speech transcripts, sentence boundaries must be inserted before most measures of syntactic complexity can be computed. In this paper, we consider how language impairments can affect segmentation methods, and compare the results of computing syntactic complexity metrics on automatically and manually segmented transcripts. We find that the important boundary indicators and the resulting segmentation accuracy can vary depending on the type of impairment observed, but that results on patient data are generally similar to control data. We also find that a number of syntactic complexity metrics are robust to the types of segmentation errors that are typically made.

156: Convolutional Neural Network for Paraphrase Identification, by Wenpeng Yin and Hinrich Schütze

We present a new deep learning architecture Bi-CNN-MI for paraphrase identification (PI). Based on the insight that PI requires comparing two sentences on multiple levels of granularity, we learn multigranular sentence representations using convolutional neural network (CNN) and model interaction features at each level. These features are then the input to a logistic classifier for PI. All parameters of the model (for embeddings, convolution and classification) are directly optimized for PI. To address the lack of training data, we pretrain the network in a novel way using a language modeling task. Results on the MSRP corpus surpass that of previous NN competitors.

671: Joint Generation of Transliterations from Multiple Representations, by Lei Yao and Grzegorz Kondrak

Machine transliteration is often referred to as phonetic translation. We show that transliterations incorporate information from both spelling and pronunciation, and propose an effective model for joint transliteration generation from both representations. We further generalize this model to include transliterations from other languages, and enhance it with re-ranking and lexicon features. We demonstrate substantial improvements in transliteration accuracy on several datasets.


89: Semantic parsing of speech using grammars learned with weak supervision, by Judith Gaspers, Philipp Cimiano, Britta Wrede

Semantic grammars can be applied both as a language model for a speech recognizer and for semantic parsing, e.g. in order to map the output of a speech recognizer into formal meaning representations. Semantic speech recognition grammars are, however, typically created manually or learned in a supervised fashion, requiring extensive manual effort in both cases. Aiming to reduce this effort, in this paper we investigate the induction of semantic speech recognition grammars under weak supervision. We present empirical results, indicating that the induced grammars support semantic parsing of speech with a rather low loss in performance when compared to parsing of input without recognition errors. Further, we show improved parsing performance compared to applying n-gram models as language models and demonstrate how our semantic speech recognition grammars can be enhanced by weights based on occurrence frequencies, yielding an improvement in parsing performance over applying unweighted grammars.

176: Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval, by Xiaodong Liu, Jianfeng Gao, Xiaodong He, Li Deng, Kevin Duh, Ye-Yi Wang

Methods of deep neural networks (DNNs) have recently demonstrated superior performance on a number of natural language processing tasks. However, in most previous work, the models are learned based on either unsupervised objectives, which does not directly optimize the desired task, or single- task supervised objectives, which often suffer from insufficient training data. We develop a multi-task DNN for learning representations across multiple tasks, not only leveraging large amounts of cross-task data, but also benefiting from a regularization effect that leads to more general representations to help tasks in new domains. Our multi-task DNN approach combines tasks of multiple-domain classification (for query classification) and information retrieval (ranking for web search), and demonstrates significant gains over strong baselines in a comprehensive set of domain adaptation and other multi-task learning experiments.

453: Prosodic boundary information helps unsupervised word segmentation, by Bogdan Ludusan, Gabriel Synnaeve, Emmanuel Dupoux

It is well known that prosodic information is used by infants in early language acquisition. In particular, prosodic boundaries have been shown to help infants with sentence and word-level segmentation. In this study, we extend an unsupervised method for word segmentation to include information about prosodic boundaries. The boundary information used was either derived from oracle data (hand-annotated), or extracted automatically with a system that employs only acoustic cues for boundary detection. The approach was tested on two different languages, English and Japanese, and the results show that boundary information helps word segmentation in both cases. The performance gain obtained for two typologically distinct languages shows the robustness of prosodic information for word segmentation. Furthermore, the improvements are not limited to the use of oracle information, similar performances being obtained also with automatically extracted boundaries.




5A: Semantics (Short Papers) — Plaza Ballroom A & B

Chair: Daniel Gildea, University of Rochester

5B: Machine Translation (Short Papers) — Plaza Ballroom D & E

Chair: David Chiang, University of Notre Dame

5C: Morphology, Syntax, Multilinguality, and Applications (Short Papers) — Plaza Ballroom F

Chair: William Lewis, Microsoft Research


281: So similar and yet incompatible: Toward the automated identification of semantically compatible words, by Germán Kruszewski and Marco Baroni

We introduce the challenge of detecting semantically compatible words, that is, words that can potentially refer to the same thing (cat and hindrance are compatible, cat and dog are not), arguing for its central role in many semantic tasks. We present a publicly available data-set of human compatibility ratings, and a neural-network model that takes distributional embeddings of words as input and learns alternative embeddings that perform the compatibility detection task quite well.

207: Morphological Modeling for Machine Translation of English-Iraqi Arabic Spoken Dialogs, by Katrin Kirchhoff, Yik-Cheung Tam, Colleen Richey, Wen Wang

This paper addresses the problem of morphological modeling in statistical speech-to-speech translation for English to Iraqi Arabic. An analysis of user data from a real-time MT-based dialog system showed that generating correct verbal inflections is a key problem for this language pair. We approach this problem by enriching the training data with morphological information derived from source-side dependency parses. We analyze the performance of several parsers as well as the effect on different types of translation models. Our method achieves an improvement of more than a full BLEU point and a significant increase in verbal inflection accuracy; at the same time, it is computationally inexpensive and does not rely on target-language linguistic tools.

647: Paradigm classification in supervised learning of morphology, by Malin Ahlberg, Markus Forsberg, Mans Hulden

Supervised morphological paradigm learning by identifying and aligning the longest common subsequence found in inflection tables has recently been proposed as a simple yet competitive way to induce morphological patterns. We combine this non-probabilistic strategy of inflection table generalization with a discriminative classifier to permit the reconstruction of complete inflection tables of unseen words. Our system learns morphological paradigms from labeled examples of inflection patterns (inflection tables) and then produces inflection tables from unseen lemmas or base forms. We evaluate the approach on datasets covering 11 different languages and show that this approach results in consistently higher accuracies vis-à-vis other methods on the same task, thus indicating that the general method is a viable approach to quickly creating high-accuracy morphological resources.


50: Do Supervised Distributional Methods Really Learn Lexical Inference Relations?, by Omer Levy, Steffen Remus, Chris Biemann, Ido Dagan

Distributional representations of words have been recently used in supervised settings for recognizing lexical inference relations between word pairs, such as hypernymy and entailment. We investigate a collection of these state-of-the-art methods, and show that they do not actually learn a relation between two words. Instead, they learn an independent property of a single word in the pair: whether that word is a ``prototypical hypernym''.

262: Continuous Adaptation to User Feedback for Statistical Machine Translation, by Frédéric Blain, Fethi Bougares, Amir Hazem, Loïc Barrault, Holger Schwenk

This paper gives a detailed experiment feedback of different approaches to adapt a statistical machine translation system towards a targeted translation project, using only small amounts of parallel in-domain data. The experiments were performed by professional translators under realistic conditions of work using a computer assisted translation tool. We analyze the influence of these adaptations on the translator productivity and on the overall post-editing effort. We show that significant improvements can be obtained by using the presented adaptation techniques.

508: Shift-Reduce Constituency Parsing with Dynamic Programming and POS Tag Lattice, by Haitao Mi and Liang Huang

We present the first dynamic programming (DP) algorithm for shift-reduce constituency parsing, which extends the DP idea of Huang and Sagae (2010) to context-free grammars. To alleviate the propagation of errors from part-of-speech tagging, we also extend the parser to take a tag lattice instead of a fixed tag sequence. Experiments on both English and Chinese treebanks show that our DP parser significantly improves parsing quality over non-DP baselines, and achieves the best accuracies among empirical linear-time parsers.


558: A Word Embedding Approach to Predicting the Compositionality of Multiword Expressions, by Bahar Salehi, Paul Cook, Timothy Baldwin

This paper presents the first attempt to use word embeddings to predict the compositionality of multiword expressions. We consider both single- and multi-prototype word embeddings. Experimental results show that, in combination with a back-off method based on string similarity, word embeddings outperform a method using count-based distributional similarity. Our best results are competitive with, or superior to, state-of-the-art methods over three standard compositionality datasets, which include two types of multiword expressions and two languages.

275: Normalized Word Embedding and Orthogonal Transform for Bilingual Word Translation, by Chao Xing, Dong Wang, Chao Liu, Yiye Lin

Word embedding has been found to be highly powerful to translate words from one language to another by a simple linear transform. However, we found some inconsistence among the objective functions of the embedding and the transform learning, as well as the distance measuring. This paper proposes a solution which normalizes the word vectors on a hypersphere and constrains the linear transform as a orthogonal transform. The experimental results confirmed that the proposed solution can offer better performance on a word similarity task and an English-to-Spanish word translation task.

513: Unsupervised Code-Switching for Multilingual Historical Document Transcription, by Dan Garrette, Hannah Alpert-Abrams, Taylor Berg-Kirkpatrick, Dan Klein

Transcribing documents from the printing press era, a challenge in its own right, is more complicated when documents interleave multiple languages---a common feature of 16th century texts. Additionally, many of these documents precede consistent orthographic conventions, making the task even harder. We extend the state-of-the-art historical OCR model of Berg-Kirkpatrick et al. (2013) to handle word-level code-switching between multiple languages. Further, we enable our system to handle spelling variability, including now-obsolete shorthand systems used by printers. Our results show average relative character error reductions of 14\% across a variety of historical texts.


577: Word Embedding-based Antonym Detection using Thesauri and Distributional Information, by Masataka Ono, Makoto Miwa, Yutaka Sasaki

This paper proposes a novel approach to train word embeddings to capture antonyms. Word embeddings have shown to capture synonyms and analogies. Such word embeddings, however, cannot capture antonyms since they depend on the distributional hypothesis. Our approach utilizes supervised synonym and antonym information from thesauri, as well as distributional information from large-scale unlabelled text data. The evaluation results on the GRE antonym question task show that our model outperforms the state-of-the-art systems and it can answer the antonym questions in the F-score of 89%.

255: Fast and Accurate Preordering for SMT using Neural Networks, by Adrià de Gispert, Gonzalo Iglesias, Bill Byrne

We propose the use of neural networks to model source-side preordering for faster and better statistical machine translation. The neural network trains a logistic regression model to predict whether two sibling nodes of the source-side parse tree should be swapped in order to obtain a more monotonic parallel corpus, based on samples extracted from the word-aligned parallel corpus. For multiple language pairs and domains, we show that this yields the best reordering performance against other state-of-the-art techniques, resulting in improved translation quality and very fast decoding.

582: Matching Citation Text and Cited Spans in Biomedical Literature: a Search-Oriented Approach, by Arman Cohan, Luca Soldaini, Nazli Goharian

Citation sentences (citances) to a reference ar- ticle have been extensively studied for sum- marization tasks. However, citances might not accurately represent the content of the cited article, as they often fail to capture the con- text of the reported findings and can be af- fected by epistemic value drift. Following the intuition behind the TAC (Text Analysis Conference) 2014 Biomedical Summarization track, we propose a system that identifies text spans in the reference article that are related to a given citance. We refer to this problem as citance-reference spans matching. We ap- proach the problem as a retrieval task; in this paper, we detail a comparison of different ci- tance reformulation methods and their combi- nations. While our results show improvement over the baseline (up to 25.9%), their absolute magnitude implies that there is ample room for future improvement.


607: A Comparison of Word Similarity Performance Using Explanatory and Non-explanatory Texts, by Lifeng Jin and William Schuler

Vectorial representations derived from large current events datasets such as Google News have been shown to perform well on word similarity tasks. This paper shows vectorial representations derived from substantially smaller explanatory text datasets such as English Wikipedia and Simple English Wikipedia preserve enough lexical semantic information to make these kinds of category judgments with equal or better accuracy. Analysis shows these results are driven by a prevalence of commonsense facts in explanatory text. These positive results for small datasets suggest vectors derived from slower but more accurate deep parsers may be practical for lexical semantic applications.

418: APRO: All-Pairs Ranking Optimization for MT Tuning, by Markus Dreyer and Yuanzhe Dong

We present APRO, a new method for machine translation tuning that can handle large feature sets. As opposed to other popular methods (e.g., MERT, MIRA, PRO), which involve randomness and require multiple runs to obtain a reliable result, APRO gives the same result on any run, given initial feature weights. APRO follows the pairwise ranking approach of PRO (Hopkins and May, 2011), but instead of ranking a small sampled subset of pairs from the k- best list, APRO efficiently ranks all pairs. By obviating the need for manually determined sampling settings, we obtain more reliable results. APRO converges more quickly than PRO and gives similar or better translation results.

350: Effective Feature Integration for Automated Short Answer Scoring, by Keisuke Sakaguchi, Michael Heilman, Nitin Madnani

A major opportunity for NLP to have a real-world impact is in helping educators score student writing, particularly content-based writing (i.e., the task of automated short answer scoring). A major challenge in this enterprise is that scored responses to a particular question (i.e., labeled data) are valuable for modeling but limited in quantity. Additional information from the scoring guidelines for humans, such as exemplars for each score level and descriptions of key concepts, can also be used. Here, we explore methods for integrating scoring guidelines and labeled responses, and we find that stacked generalization (Wolpert, 1992) improves performance, especially for small training sets.




6A: Generation and Summarization (Long Papers) — Plaza Ballroom A & B

Chair: Wei Xu, University of Pennsylvania

6B: Discourse and Coreference (Long Papers) — Plaza Ballroom D & E

Chair: Ani Nenkova, University of Pennsylvania

6C: Information Extraction and Question Answering (Long Papers) — Plaza Ballroom F

Chair: Lucy Vanderwende, Microsoft Research


565: Socially-Informed Timeline Generation for Complex Events, by Lu Wang, Claire Cardie, Galen Marchetti

Existing timeline generation systems for complex events consider only information from traditional media, ignoring the rich social context provided by user-generated content that reveals representative public interests or insightful opinions. We instead aim to generate socially-informed timelines that contain both news article summaries and selected user comments. We present an optimization framework designed to balance topical cohesion between the article and comment summaries along with their informativeness and coverage of the event. Automatic evaluations on real-world datasets that cover four complex events show that our system produces more informative timelines than state-of-the-art systems. In human evaluation, the associated comment summaries are furthermore rated more insightful than editor’s picks and comments ranked highly by users.

36: Encoding World Knowledge in the Evaluation of Local Coherence, by Muyu Zhang, Vanessa Wei Feng, Bing Qin, Graeme Hirst, Ting Liu, Jingwen Huang

Previous work on text coherence was primarily based on matching multiple mentions of the same entity in different parts of the text; therefore, it misses the contribution from semantically related but not necessarily coreferential entities (e.g., Gates and Microsoft). In this paper, we capture such semantic relatedness by leveraging world knowledge (e.g., Gates is the person who created Microsoft), and use two existing evaluation frameworks. First, in the unsupervised framework, we introduce semantic relatedness as an enrichment to the original graph-based model of Guinaudeau and Strube (2013). In addition, we incorporate semantic relatedness as additional features into the popular entity-based model of Barzilay and Lapata (2008). Across both frameworks, our enriched model with semantic relatedness outperforms the original methods, especially on short documents.

476: Injecting Logical Background Knowledge into Embeddings for Relation Extraction, by Tim Rocktäschel, Sameer Singh, Sebastian Riedel

Matrix factorization approaches to relation extraction provide several attractive features: they support distant supervision, handle open schemas, and leverage unlabeled data. Unfortunately, these methods share a shortcoming with all other distantly supervised approaches: they cannot learn to extract target relations without existing data in the knowledge base, and likewise, these models are inaccurate for relations with sparse data. Rule-based extractors, on the other hand, can be easily extended to novel relations and improved for existing but inaccurate relations, through first-order formulae that capture auxiliary domain knowledge. However, usually a large set of such formulae is necessary to achieve generalization.

In this paper, we introduce a paradigm for learning low-dimensional embeddings of entity-pairs and relations that combine the advantages of matrix factorization with first-order logic domain knowledge. We introduce simple approaches for estimating such embeddings, as well as a novel training algorithm to jointly optimize over factual and first-order logic information. Our results show that this method is able to learn accurate extractors with little or no distant supervision alignments, while at the same time generalizing to textual patterns that do not appear in the formulae.


254: Movie Script Summarization as Graph-based Scene Extraction, by Philip John Gorinski and Mirella Lapata

In this paper we study the task of movie script summarization, which we argue could enhance script browsing, give readers a rough idea of the script's plotline, and speed up reading time. We formalize the process of generating a shorter version of a screenplay as the task of finding an optimal chain of scenes. We develop a graph-based model that selects a chain by jointly optimizing its logical progression, diversity, and importance. Human evaluation based on a question-answering task shows that our model produces summaries which are more informative compared to competitive baselines.

673: Chinese Event Coreference Resolution: An Unsupervised Probabilistic Model Rivaling Supervised Resolvers, by Chen Chen and Vincent Ng

Recent work has successfully leveraged the semantic information extracted from lexical knowledge bases such as WordNet and FrameNet to improve English event coreference resolvers. The lack of comparable resources in other languages, however, has made the design of high-performance non-English event coreference resolvers, particularly those employing unsupervised models, very difficult. We propose a generative model for the under-studied task of Chinese event coreference resolution that rivals its supervised counterparts in performance when evaluated on the ACE 2005 corpus.

47: Unsupervised Entity Linking with Abstract Meaning Representation, by Xiaoman Pan, Taylor Cassidy, Ulf Hermjakob, Heng Ji, Kevin Knight

Most successful Entity Linking (EL) methods aim to link mentions to their referent entities in a structured Knowledge Base (KB) by comparing their respective contexts, often using similarity measures. While the KB structure is given, current methods have suffered from impoverished information representations on the mention side. In this paper, we demonstrate the effectiveness of Abstract Meaning Representation (AMR) (Banarescu et al., 2013) to select high quality sets of entity ``collaborators'' to feed a simple similarity measure (Jaccard) to link entity mentions. Experimental results show that AMR captures contextual properties discriminative enough to make linking decisions, without the need for EL training data, and that system with AMR parsing output outperforms hand labeled traditional semantic roles as context representation for EL. Finally, we show promising preliminary results for using AMR to select sets of ``coherent'' entity mentions for collective entity linking.


567: Toward Abstractive Summarization Using Semantic Representations, by Fei Liu, Jeffrey Flanigan, Sam Thomson, Norman Sadeh, Noah A. Smith

We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR). In this framework, the source text is parsed to a set of AMR graphs, the graphs are transformed into a summary graph, and then text is generated from the summary graph. We focus on the graph-to-graph transformation that reduces the source semantic graph into a summary graph, making use of an existing AMR parser and assuming the eventual availability of an AMR-to-text generator. The framework is data-driven, trainable, and not specifically designed for a particular domain. Experiments on gold-standard AMR annotations and system parses show promising results. Code is available at:

535: Removing the Training Wheels: A Coreference Dataset that Entertains Humans and Challenges Computers, by Anupam Guha, Mohit Iyyer, Danny Bouman, Jordan Boyd-Graber

Coreference is a core NLP problem. However, newswire data, the primary source of existing coreference data, lack the richness necessary to truly solve coreference. We present a new domain with denser references---quiz bowl questions---that is challenging and enjoyable to humans, and we use the quiz bowl community to develop a new coreference dataset, together with an annotation framework that can tag any text data with coreferences and named entities. We also successfully integrate active learning into this annotation pipeline to collect documents maximally useful to coreference models. State-of-the-art coreference systems underperform a simple classifier on our new dataset, motivating non-newswire data for future coreference research.

317: Idest: Learning a Distributed Representation for Event Patterns, by Sebastian Krause, Enrique Alfonseca, Katja Filippova, Daniele Pighin

This paper describes Idest, a new method for learning paraphrases of event patterns. It is based on a new neural network architecture that only relies on the weak supervision signal that comes from the news published on the same day and mention the same real-world entities. It can generalize across extractions from different dates to produce a robust paraphrase model for event patterns that can also capture meaningful representations for rare patterns. We compare it with two state-of-the-art systems and show that it can attain comparable quality when trained on a small dataset. Its generalization capabilities also allow it to leverage much more data, leading to substantial quality improvements.




7A: Semantics (Long + TACL Papers) — Plaza Ballroom A & B

Chair: Xiaodong He, Microsoft Research

7B: Information Extraction and Question Answering (Long + TACL Papers) — Plaza Ballroom D & E

Chair: Vincent Ng, University of Texas at Dallas

7C: Machine Translation (Long Papers) — Plaza Ballroom F

Chair: Hany Hassan, Microsoft Research


573: High-Order Low-Rank Tensors for Semantic Role Labeling, by Tao Lei, Yuan Zhang, Lluís Màrquez, Alessandro Moschitti, Regina Barzilay

This paper introduces a tensor-based approach to semantic role labeling (SRL). The motivation behind the approach is to automatically induce a compact feature representation for words and their relations, tailoring them to the task. In this sense, our dimensionality reduction method provides a clear alternative to the traditional feature engineering approach used in SRL. To capture meaningful interactions between the argument, predicate, their syntactic path and the corresponding role label, we compress each feature representation first to a lower dimensional space prior to assessing their interactions. This corresponds to using an overall cross-product feature representation and maintaining associated parameters as a four-way low-rank tensor. The tensor parameters are optimized for the SRL performance using standard online algorithms. Our tensor-based approach rivals the best performing system on the CoNLL-2009 shared task. In addition, we demonstrate that adding the representation tensor to a competitive tensor-free model yields 2\% absolute increase in F-score.

369: Lexical Event Ordering with an Edge-Factored Model, by Omri Abend, Shay B. Cohen, Mark Steedman

Extensive lexical knowledge is necessary for temporal analysis and planning tasks. We ad- dress in this paper a lexical setting that allows for the straightforward incorporation of rich features and structural constraints. We explore a lexical event ordering task, namely determining the likely temporal order of events based solely on the identity of their predicates and arguments. We propose an “edge-factored” model for the task that decomposes over the edges of the event graph. We learn it using the structured perceptron. As lexical tasks require large amounts of text, we do not attempt manual annotation and instead use the textual order of events in a domain where this order is aligned with their temporal order, namely cooking recipes.

71: Bag-of-Words Forced Decoding for Cross-Lingual Information Retrieval, by Felix Hieber and Stefan Riezler

Current approaches to cross-lingual information retrieval (CLIR) rely on standard retrieval models into which query translations by statistical machine translation (SMT) are integrated at varying degree. In this paper, we present an attempt to turn this situation on its head: Instead of the retrieval aspect, we emphasize the translation component in CLIR. We perform search by using an SMT decoder in forced decoding mode to produce a bag-of-words representation of the target documents to be ranked. The SMT model is extended by retrieval-specific features that are optimized jointly with standard translation features for a ranking objective. We find significant gains over the state-of-the-art in a large-scale evaluation on cross-lingual search in the domains patents and Wikipedia.


TACL-398: Large-scale Semantic Parsing without Question-Answer Pairs, by Siva Reddy, Mirella Lapata, Mark Steedman

In this paper we introduce a novel semantic parsing approach to query Freebase in natural language without requiring manual annotations or question-answer pairs. Our key insight is to represent natural language via semantic graphs whose topology shares many commonalities with Freebase. Given this representation, we conceptualize semantic parsing as a graph matching problem. Our model converts sentences to semantic graphs using CCG and subsequently grounds them to Freebase guided by denotations as a form of weak supervision. Evaluation experiments on a subset of the Free917 and WebQuestions benchmark datasets show our semantic parser improves over the state of the art.

TACL-494: Entity disambiguation with web links, by Andrew Chisholm, Ben Hachey

Entity disambiguation with Wikipedia relies on structured information from redirect pages, article text, inter-article links, and categories. We explore whether web links can replace a curated encyclopaedia, obtaining entity prior, name, context, and coherence models from a corpus of web pages with links to Wikipedia. Experiments compare web link models to Wikipedia models on well-known CoNLL and TAC data sets. Results show that using 34 million web links approaches Wikipedia performance. Combining web link and Wikipedia models produces the best-known disambiguation accuracy of 88.7 on standard newswire test data.

293: Accurate Evaluation of Segment-level Machine Translation Metrics, by Yvette Graham, Timothy Baldwin, Nitika Mathur

Evaluation of segment-level machine translation metrics is currently hampered by: (1) low inter-annotator agreement levels in human assessments; (2) lack of an effective mechanism for evaluation of translations of equal quality; and (3) lack of methods of significance testing improvements over a baseline. In this paper, we provide solutions to each of these challenges and outline a new human evaluation methodology aimed specifically at assessment of segment-level metrics. We replicate the human evaluation component of WMT-13 and reveal that the current state-of-the-art performance of segment-level metrics is better than previously believed. Three segment-level metrics --- Meteor, nLepor and sentBLEU-moses --- are found to correlate with human assessment at a level not significantly outperformed by any other metric in both the individual language pair assessment for Spanish to English and the aggregated set of 9 language pairs.


TACL-457: A Large Scale Evaluation of Distributional Semantic Models: Parameters, Interactions and Model Selection, by Gabriella Lapesa, Stefan Evert

This paper presents the results of a large-scale evaluation study of window-based Distributional Semantic Models on a wide variety of tasks. Our study combines a broad coverage of model parameters with a model selection methodology that is robust to overfitting and able to capture parameter interactions. We show that our strategy allows us to identify parameter configurations that achieve good performance across different datasets and tasks.

TACL-412: A Joint Model for Entity Analysis: Coreference, Typing, and Linking, by Greg Durrett and Dan Klein

We present a joint model of three core tasks in the entity analysis stack: coreference resolution (within-document clustering), named entity recognition (coarse semantic typing), and entity linking (matching to Wikipedia entities). Our model is formally a structured conditional random field. Unary factors encode local features from strong baselines for each task. We then add binary and ternary factors to capture cross-task interactions, such as the constraint that coreferent mentions have the same semantic type. On the ACE 2005 and OntoNotes datasets, we achieve state-of-the-art results for all three tasks. Moreover, joint modeling improves performance on each task over strong independent baselines.

532: Leveraging Small Multilingual Corpora for SMT Using Many Pivot Languages, by Raj Dabre, Fabien Cromieres, Sadao Kurohashi, Pushpak Bhattacharyya

We present our work on leveraging multilingual parallel corpora of small sizes for Statistical Machine Translation between Japanese and Hindi using multiple pivot languages. In our setting, the source and target part of the corpus remains the same, but we show that using several different pivot to extract phrase pairs from these source and target parts lead to large BLEU improvements. We focus on a variety of ways to exploit phrase tables generated using multiple pivots to support a direct source-target phrase table. Our main method uses the Multiple Decoding Paths (MDP) feature of Moses, which we empirically verify as the best compared to the other methods we used. We compare and contrast our various results to show that one can overcome the limitations of small corpora by using as many pivot languages as possible in a multilingual setting. Most importantly, we show that such pivoting aids in learning of additional phrase pairs which are not learned when the direct source-target corpus is small. We obtained improvements of up to 3 BLEU points using multiple pivots for Japanese to Hindi translation compared to when only one pivot is used. To the best of our knowledge, this work is also the first of its kind to attempt the simultaneous utilization of 7 pivot languages at decoding time.


Poster session 2A: Short papers — Plaza Exhibits All


77: Context-Dependent Automatic Response Generation Using Statistical Machine Translation Techniques, by Andrew Shin, Ryohei Sasano, Hiroya Takamura, Manabu Okumura

Developing a system that can automatically respond to a user's utterance has recently become a topic of research in natural language processing. However, most works on the topic take into account only a single preceding utterance to generate a response. Recent works demonstrate that the application of statistical machine translation (SMT) techniques towards monolingual dialogue setting, in which a response is treated as a translation of a stimulus, has a great potential, and we exploit the approach to tackle the context-dependent response generation task. We attempt to extract relevant and significant information from the wider contextual scope of the conversation, and incorporate it into the SMT techniques. We also discuss the advantages and limitations of this approach through our experimental results.

83: Distributed Representations of Words to Guide Bootstrapped Entity Classifiers, by Sonal Gupta and Christopher D. Manning

Bootstrapped classifiers iteratively generalize from a few seed examples or prototypes to other examples of target labels. However, sparseness of language and limited supervision make the task difficult. We address this problem by using distributed vector representations of words to aid the generalization. We use the word vectors to expand entity sets used for training classifiers in a bootstrapped pattern-based entity extraction system. Our experiments show that the classifiers trained with the expanded sets perform better on entity extraction from four online forums, with 30% F1 improvement on one forum. The results suggest that distributed representations can provide good directions for generalization in a bootstrapping system.

103: Multilingual Open Relation Extraction Using Cross-lingual Projection, by Manaal Faruqui and Shankar Kumar

Open domain relation extraction systems identify relation and argument phrases in a sentence without relying on any underlying schema. However, current state-of-the-art relation extraction systems are available only for English because of their heavy reliance on linguistic tools such as part-of-speech taggers and dependency parsers. We present a cross-lingual annotation projection method for language independent relation extraction. We evaluate our method on a manually annotated test set and present results on three typologically different languages. We release these manual annotations and extracted relations in ten languages from Wikipedia.

145: Exploiting Text and Network Context for Geolocation of Social Media Users, by Afshin Rahimi, Duy Vu, Trevor Cohn, Timothy Baldwin

Research on automatically geolocating social media users has conventionally been based on the text content of posts from a given user or the social network of the user, with very little crossover between the two, and no benchmarking of the two approaches over comparable datasets. We bring the two threads of research together in first proposing a text-based method based on adaptive grids, followed by a hybrid network- and text-based method. Evaluating over three Twitter datasets, we show that the empirical difference between text- and network-based methods is not great, and that hybridisation of the two is superior to the component methods, especially in contexts where the user graph is not well connected. We achieve state-of-the-art results on all three datasets.

197: Unsupervised Most Frequent Sense Detection using Word Embeddings, by Sudha Bhingardive, Dhirendra Singh, Rudramurthy V, Hanumant Redkar, Pushpak Bhattacharyya

An acid test for any new Word Sense Disambiguation (WSD) algorithm is its performance against the Most Frequent Sense (MFS). The field of WSD has found the MFS baseline very hard to beat. Clearly, if WSD researchers had access to MFS values, their striving to better this heuristic will push the WSD frontier. However, getting MFS values requires sense marked corpus in enormous amount, which is out of bounds for most languages, even if their WordNets are available. In this paper, we propose an unsupervised method for MFS detection from the untagged corpora, which exploits word embeddings. \textit{We compare the word embeddings of a word with all its sense embeddings and obtain the predominant sense with the highest similarity.} We observe significant performance gain for Hindi WSD over the WordNet First Sense (WFS) baseline. As for English, the SemCor baseline is bettered for those words whose frequency is greater than 2. Our approach is language and domain independent.

217: Chain Based RNN for Relation Classification, by Javid Ebrahimi and Dejing Dou

We present a novel approach for relation classification, using a recursive neural network (RNN), based on the shortest path between two entities in a dependency graph. Previous works on RNN are based on constituency-based parsing because phrasal nodes in a parse tree can capture compositionality in a sentence. Compared with constituency-based parse trees, dependency graphs can represent relations more compactly. This is particularly important in sentences with distant entities, where the parse tree spans words that are not relevant to the relation. In such cases RNN cannot be trained effectively in a timely manner. However, due to the lack of phrasal nodes in dependency graphs, application of RNN is not straightforward. In order to tackle this problem, we utilize dependency constituent units called chains. Our experiments on two relation classification datasets show that Chain based RNN provides a shallower network, which performs considerably faster and achieves better classification results.

223: CASSA: A Context-Aware Synonym Simplification Algorithm, by Ricardo Baeza-Yates, Luz Rello, Julia Dembowski

We present a new context-aware method for lexical simplification that uses two free lan- guage resources and real web frequencies. We compare it with the state-of-the-art method for lexical simplification in Spanish and the established simplification baseline, that is, the most frequent synonym. Our method improves upon the other methods in the detection of complex words, in meaning preservation, and in simplicity. Although we use Spanish, the method can be extended to other languages since it does not require alignment of parallel corpora.

237: Mining for unambiguous instances to adapt part-of-speech taggers to new domains, by Dirk Hovy, Barbara Plank, Héctor Martínez Alonso, Anders Søgaard

We present a simple, yet effective approach to adapt part-of-speech (POS) taggers to new domains. Our approach only requires a dictionary and large amounts of unlabeled target data. The idea is to use the dictionary to mine the unlabeled target data for unambiguous word sequences, thus effectively collecting labeled target data. We add the mined instances to available labeled newswire data to train a POS tagger for the target domain. The induced models significantly improve tagging accuracy on held-out test sets across three domains (Twitter, spoken language, and search queries). We also present results for Dutch, Spanish and Portuguese Twitter data, and provide two novel manually-annotated test sets.

305: On the Automatic Learning of Sentiment Lexicons, by Aliaksei Severyn and Alessandro Moschitti

This paper describes a simple and principled approach to automatically construct sentiment lexicons using distant supervision. We induce the sentiment association scores for the lexicon items from a model trained on a weakly supervised corpora. Our empirical findings show that features extracted from such a machine-learned lexicon outperform models using manual or other automatically constructed sentiment lexicons. Finally, our system achieves the state-of-the-art in Twitter Sentiment Analysis tasks from Semeval-2013 and ranks 2nd best in Semeval-2014 according to the average rank.

311: Development of the Multilingual Semantic Annotation System, by Scott Piao, Francesca Bianchi, Carmen Dayrell, Angela D'Egidio, Paul Rayson

This paper reports on our research to generate multilingual semantic lexical resources and develop multilingual semantic annotation software, which assigns each word in running text to a semantic category based on a lexical semantic classification scheme. Such tools have an important role in developing intelli-gent multilingual NLP, text mining and ICT systems. In this work, we aim to extend an existing English semantic annotation tool to cover a range of languages, namely Italian, Chinese and Brazilian Portuguese, by boot-strapping new semantic lexical resources via automatically translating existing English se-mantic lexicons into these languages. We used a set of bilingual dictionaries and word lists for this purpose. In our experiment, with minor manual improvement of the automatically generated semantic lexicons, the prototype tools based on the new lexicons achieved an average lexical coverage of 79.86% and an average annotation precision of 71.42% (if only precise annotations are considered) or 84.64% (if partially correct annotations are included) on the three languages. Our experiment demonstrates that it is feasible to rapidly develop prototype semantic annotation tools for new languages by automatically bootstrapping new semantic lexicons based on existing ones.

385: Unediting: Detecting Disfluencies Without Careful Transcripts, by Victoria Zayats, Mari Ostendorf, Hannaneh Hajishirzi

Speech transcripts often only capture semantic content, omitting disfluencies that can be useful for analyzing social dynamics of a discussion. This work describes steps in building a model that can recover a large fraction of locations where disfluencies were present, by transforming carefully annotated text to match the standard transcription style, introducing a two-stage model for handling different types of disfluencies, and applying semi-supervised learning. Experiments show improvement in disfluency detection on Supreme Court oral arguments, nearly 23% improvement in F1.

427: Type-Driven Incremental Semantic Parsing with Polymorphism, by Kai Zhao and Liang Huang

Semantic parsing has made significant progress, but most current semantic parsers are extremely slow (CKY-based) and rather primitive in representation. We introduce three new techniques to tackle these problems. First, we design the first linear-time incremental shift-reduce-style semantic parsing algorithm which is more efficient than conventional cubic-time bottom-up semantic parsers. Second, our parser, being type-driven instead of syntax-driven, uses type-checking to decide the direction of reduction, which eliminates the need for a syntactic grammar such as CCG. Third, to fully exploit the power of type-driven semantic parsing beyond simple types (such as entities and truth values), we borrow from programming language theory the concepts of subtype polymorphism and parametric polymorphism to enrich the type system in order to better guide the parsing. Our system learns very accurate parses in GeoQuery, Jobs and Atis domains.

451: Template Kernels for Dependency Parsing, by Hillel Taub-Tabib, Yoav Goldberg, Amir Globerson

A common approach to dependency parsing is scoring a parse via a linear function of a set of indicator features. These features are typically manually constructed from templates that are applied to parts of the parse tree. The templates define which properties of a part should combine to create features. Existing approaches consider only a small subset of the possible combinations, due to statistical and computational efficiency considerations. In this work we present a novel kernel which facilitates efficient parsing with feature representations corresponding to a much larger set of combinations. We integrate the kernel into a parse reranking system and demonstrate its effectiveness on four languages from the CoNLL-X shared task.

459: Embedding a Semantic Network in a Word Space, by Richard Johansson and Luis Nieto Piña

We present a framework for using continuous-space vector representations of word meaning to derive new vectors representing the meaning of senses listed in a semantic network. It is a post-processing approach that can be applied to several types of word vector representations. It uses two ideas: first, that vectors for polysemous words can be decomposed into a mix of sense vectors; secondly, that the vector for a sense is kept similar to those of its neighbors in the network. This leads to a constrained optimization problem, and we present an approximation for the case when the distance function is the squared Euclidean.

We applied this algorithm on a Swedish semantic network, and we evaluate the quality of the resulting sense representations extrinsically by showing that they give large improvements when used in a classifier that creates lexical units for FrameNet frames.

501: Identification and Characterization of Newsworthy Verbs in World News, by Benjamin Nye and Ani Nenkova

We present a data-driven technique for acquiring domain-level importance of verbs from the analysis of abstract/article pairs of world news articles. We show that existing lexical resources capture some the semantic characteristics for important words in the domain. We develop a novel characterization of the association between verbs and personal story narratives, which is descriptive of verbs avoided in summaries for this domain.

545: Enhancing Sumerian Lemmatization by Unsupervised Named-Entity Recognition, by Yudong Liu, Clinton Burkhart, James Hearne, Liang Luo

Lemmatization for the Sumerian language, compared to the modern languages, is much more challenging due to that it is a long dead language, highly skilled language experts are extremely scarce and more and more Sumerian texts are coming out. This paper describes how our unsupervised Sumerian named-entity recognition (NER) system helps to improve the lemmatization of the Cuneiform Digital Library Initiative (CDLI), a specialist database of cuneiform texts, from the Ur III period. Experiments show that a promising improvement in personal name annotation in such texts and a substantial reduction in expert annotation effort can be achieved by leveraging our system with minimal seed annotation.

611: Improving Update Summarization via Supervised ILP and Sentence Reranking, by Chen Li, Yang Liu, Lin Zhao

Integer Linear Programming (ILP) based summarization methods have been widely adopted recently because of their state-of-the-art performance. This paper proposes two new modifications in this framework for update summarization. Our key idea is to use discriminative models with a set of features to measure both the salience and the novelty of words and sentences. First, these features are used in a supervised model to predict the weights of the concepts used in the ILP model. Second, we generate preliminary sentence candidates in the ILP model and then rerank them using sentence level features. We evaluate our method on different TAC update summarization data sets, and the results show that our system performs competitively compared to the best TAC systems based on the ROUGE evaluation metric.

651: Reserating the awesometastic: An automatic extension of the WordNet taxonomy for novel terms, by David Jurgens and Mohammad Taher Pilehvar

This paper presents CROWN, an automatically constructed extension of WordNet that augments its taxonomy with novel lemmas from Wiktionary. CROWN fills the important gap in WordNet's lexicon for slang, technical, and rare lemmas, and more than doubles its current size. In two evaluations, we demonstrate that the construction procedure is accurate and has a significant impact on a WordNet-based algorithm encountering novel lemmas.

669: Everyone Likes Shopping! Multi-class Product Categorization for e-Commerce, by Zornitsa Kozareva

Online shopping caters the needs of millions of users on a daily basis. To build an accurate system that can retrieve relevant products for a query like "MB252 with travel bags" one requires product and query categorization mechanisms, which classify the text as "Home&Garden >Kitchen&Dining >Kitchen Appliances >Blenders". One of the biggest challenges in e-Commerce is that providers like Amazon, e-Bay, Google, Yahoo! and Walmart organize products into different product taxonomies making it hard and time-consuming for sellers to categorize goods for each shopping platform.

To address this challenge, we propose an automatic product categorization mechanism, which for a given product title assigns the correct product category from a taxonomy. We conducted an empirical evaluation on 445,408 product titles and used a rich product taxonomy of 319 categories organized into 6 levels. We compared performance against multiple algorithms and found that the best performing system reaches .88 f-score.

675: Cross-lingual Text Classification Using Topic-Dependent Word Probabilities, by Daniel Andrade, Kunihiko Sadamasa, Akihiro Tamura, Masaaki Tsuchida

Cross-lingual text classification is a major challenge in natural language processing, since often training data is available in only one language (target language), but not available for the language of the document we want to classify (source language). Here, we propose a method that only requires a bilingual dictionary to bridge the language gap. Our proposed probabilistic model allows us to estimate translation probabilities that are conditioned on the whole source document. The assumption of our probabilistic model is that each document can be characterized by a distribution over topics that help to solve the translation ambiguity of single words. Using the derived translation probabilities, we then calculate the expected word frequency of each word type in the target language. Finally, these expected word frequencies can be used to classify the source text with any classifier that was trained using only target language documents. Our experiments confirm the usefulness of our proposed method.


System demonstrations — Plaza Exhibits All


D11: Two Practical Rhetorical Structure Theory Parsers, by Mihai Surdeanu, Tom Hicks and Marco Antonio Valenzuela-Escarcega

We describe the design, development, and API for two discourse parsers for Rhetorical Structure Theory. The two parsers use the same underlying framework, but one uses features that rely on dependency syntax, produced by a fast shift-reduce parser, whereas the other uses a richer feature space, including both constituent- and dependency-syntax and coreference information, produced by the Stanford CoreNLP toolkit. Both parsers obtain state-of-the-art performance, and use a very simple API consisting of, minimally, two lines of Scala code. We accompany this code with a visualization library that runs the two parsers in parallel, and displays the two generated discourse trees side by side, which provides an intuitive way of comparing the two parsers.

D31: An AMR parser for English, French, German, Spanish and Japanese and a new AMR-annotated corpus, by Lucy Vanderwende, Arul Menezes and Chris Quirk

In this demonstration, we will present our online parser that allows users to submit any sentence and obtain an analysis following the specification of AMR (Banarescu et al., 2014) to a large extent. This AMR analysis is generated by a small set of rules that convert a native Logical Form analysis provided by a pre-existing parser into the AMR format. While we demonstrate the performance of our AMR parser on data sets annotated by the LDC, we will focus attention in the demo on the following two areas: 1) we will make available AMR annotations for the data sets that were used to develop our parser, to serve as a supplement to the LDC data sets, and 2) we will demonstrate AMR parsers for German, French, Spanish and Japanese that make use of the same small set of LF-to-AMR conversion rules.

D46: SETS: Scalable and Efficient Tree Search in Dependency Graphs, by Juhani Luotolahti, Jenna Kanerva, Sampo Pyysalo and Filip Ginter

We present a syntactic analysis query toolkit geared specifically towards massive dependency parsebanks and morphologically rich languages. The query language allows arbitrary tree queries, including negated branches, and is suitable for querying analyses with rich morphological annotation. Treebanks of over a million words can be comfortably queried on a low-end netbook, and a parsebank with over 100M words on a single consumer-grade server. We also introduce a web-based interface for interactive querying. All contributions are available under open licenses.

D57: Using Word Semantics To Assist English as a Second Language Learners, by Mahmoud Azab, Chris Hokamp and Rada Mihalcea

We introduce an interactive interface that aims to help English as a Second Language (ESL) students overcome language related hindrances while reading a text. The interface allows the user to find supplementary information on selected difficult words. The interface is empowered by our lexical substitution engine that provides context-based synonyms for difficult words. We also provide a practical solution for a real-world usage scenario. We demonstrate using the lexical substitution engine -- as a browser extension that can annotate and disambiguate difficult words on any webpage.

D16: hyp: A Toolkit for Representing, Manipulating, and Optimizing Hypergraphs, by Markus Dreyer and Jonathan Graehl

We present hyp, an open-source toolkit for the representation, manipulation, and optimization of weighted directed hypergraphs. hyp provides compose, project, invert functionality, k-best path algorithms, the inside and outside algorithms, and more. Finite-state machines are modeled as a special case of directed hypergraphs. hyp consists of a C++ API, as well as a command line tool, and is available for download at

D37: Natural Language Question Answering and Analytics for Diverse and Interlinked Datasets, by Dezhao Song, Frank Schilder, Charese Smiley and Chris Brew

Previous systems for natural language questions over complex linked datasets require the user to enter a complete and well-formed question, and present the answers as raw lists of entities. Using a feature-based grammar with a full formal semantics, we have developed a system that is able to support rich autosuggest, and to deliver dynamically generated analytics for each result that it returns.

D34: ICE: Rapid Information Extraction Customization for NLP Novices, by Yifan He and Ralph Grishman

We showcase ICE, an Integrated Customization Environment for Information Extraction. ICE is an easy tool for non-NLP experts to rapidly build customized IE systems for a new domain.

D40: ELCO3: Entity Linking with Corpus Coherence Combining Open Source Annotators, by Pablo Ruiz, Thierry Poibeau and Fréderique Mélanie

Entity Linking (EL) systems' performance is uneven across corpora or depending on entity types. To help overcome this issue, we propose an EL workflow that combines the outputs of several open source EL systems, and selects annotations via weighted voting. The results are displayed on a UI that allows the users to navigate the corpus and to evaluate annotation quality based on several metrics.

D12: Analyzing and Visualizing Coreference Resolution Errors, by Sebastian Martschat, Thierry Göckel and Michael Strube

We present a toolkit for coreference resolution error analysis. It implements a recently proposed analysis framework and contains rich components for analyzing and visualizing recall and precision errors.

D29: RExtractor: a Robust Information Extractor, by Vincent Kríž and Barbora Hladka

The RExtractor system is an information extractor that processes input documents by natural language processing tools and consequently queries the parsed sentences to extract a knowledge base of entities and their relations. The extraction queries are designed manually using a tool that enables natural graphical representation of queries over dependency trees. A workflow of the system is designed to be language and domain independent. We demonstrate RExtractor on Czech and English legal documents.

D61: WOLFE: An NLP-friendly Declarative Machine Learning Stack, by Sameer Singh, Tim Rocktäschel, Luke Hewitt, Jason Naradowsky and Sebastian Riedel

Developing machine learning algorithms for natural language processing (NLP) applications is inherently an iterative process, involving a continuous refinement of the choice of model, engineering of features, selection of inference algorithms, search for the right hyper- parameters, and error analysis. Existing probabilistic program languages (PPLs) only provide partial solutions; most of them do not support commonly used models such as matrix factorization or neural networks, and do not facilitate interactive and iterative programming that is crucial for rapid development of these models.

In this demo we introduce WOLFE, a stack designed to facilitate the development of NLP applications: (1) the WOLFE language allows the user to concisely define complex models, enabling easy modification and extension, (2) the WOLFE interpreter transforms declarative ma- chine learning code into automatically differentiable terms or, where applicable, into factor graphs that allow for complex models to be applied to real-world applications, and (3) the WOLFE IDE provides a number of different visual and interactive elements, allowing intuitive exploration and editing of the data representations, the underlying graphical models, and the execution of the inference algorithms.

D35: AMRICA: an AMR Inspector for Cross-language Alignments, by Naomi Saphra and Adam Lopez

Abstract Meaning Representation (AMR), an annotation scheme for natural language semantics, has drawn attention for its simplicity and representational power. Because AMR annotations are not designed for human readability, we present AMRICA, a visual aid for exploration of AMR annotations. AMRICA can visualize an AMR or the difference between two AMRs to help users diagnose interannotator disagreement or errors from an AMR parser. AMRICA can also automatically align and visualize the AMRs of a sentence and its translation in a parallel text. We believe AMRICA will simplify and streamline exploratory research on cross-lingual AMR corpora.

D5: A Web Application for Automated Dialect Analysis, by Sravana Reddy and James Stanford

Sociolinguists are regularly faced with the task of measuring phonetic features from speech, which involves manually transcribing audio recordings -- a major bottleneck to analyzing large collections of data. We harness automatic speech recognition to build an online end-to-end web application where users upload untranscribed speech collections and receive formant measurements of the vowels in their data. We demonstrate this tool by using it to automatically analyze President Barack Obama's vowel pronunciations.

D55: Question Answering System using Multiple Information Source and Open Type Answer Merge, by Seonyeong Park, Soonchoul Kwon, Byungsoo Kim, Sangdo Han, Hyosup Shim, Gary Geunbae Lee and Gary Geunbae Lee

This paper presents a multi-strategy and multi-source question answering (QA) system that can use multiple strategies to both answer natural language (NL) questions and respond to keywords. We use multiple information sources including curated knowledge base, raw text, auto-generated triples, and NL processing results. We develop open semantic answer type detector for answer merging and improve previous developed single QA modules such as knowledge base based QA, information retrieval based QA.

D14: Brahmi-Net: A transliteration and script conversion system for languages of the Indian subcontinent, by Anoop Kunchukuttan, Ratish Puduppully and Pushpak Bhattacharyya

We present Brahmi-Net - an online system for transliteration and script conversion for all major Indian language pairs (306 pairs). The system covers 13 Indo-Aryan languages, 4 Dravidian languages and English. For training the transliteration systems, we mined parallel transliteration corpora from parallel translation corpora using an unsupervised method and trained statistical transliteration systems using the mined corpora. Languages which do not have a parallel corpora are supported by transliteration through a bridge language. Our script conversion system supports conversion between all Brahmi-derived scripts as well as ITRANS romanization scheme. For this, we leverage co-ordinated Unicode ranges between Indic scripts and use an extended ITRANS encoding for transliterating between English and Indic scripts. The system also provides top-k transliterations and simultaneous transliteration into multiple output languages. We provide a Python as well as REST API to access these services. The API and the mined transliteration corpus are made available for research use under an open source license.

D9: An Open-source Framework for Multi-level Semantic Similarity Measurement, by Mohammad Taher Pilehvar and Roberto Navigli

We present an open source, freely available Java implementation of Align, Disambiguate, and Walk (ADW), a state-of-the-art approach for measuring semantic similarity based on the Personalized PageRank algorithm. A pair of linguistic items, such as phrases or sentences, are first disambiguated using an alignment-based disambiguation technique and then modeled using random walks on the WordNet graph. ADW provides three main advantages: (1) it is applicable to all types of linguistic items, from word senses to texts; (2) it is all-in-one, i.e., it does not need any additional resource, training or tuning; and (3) it has proven to be highly reliable at different lexical levels and multiple evaluation benchmarks. We are releasing the source code at We also provide at a Web interface and a Java API that can be seamlessly integrated into other NLP systems requiring semantic similarity measurement.

D51: WriteAhead2: Mining Lexical Grammar Patterns for Assisted Writing, by Jim Chang and Jason Chang

This paper describes WriteAhead2, an interactive writing environment that provides lexical and grammatical suggestions for second language learners, and helps them write fluently and avoid common writing errors. The method involves learning phrase templates from dictionary examples, and extracting grammar patterns with example phrases from an academic corpus. At run-time, as the user types word after word, the actions trigger a list after list of suggestions. Each successive list contains grammar patterns and examples, most relevant to the half-baked sentence. WriteAhead2 facilitates steady, timely, and spot-on interactions between learner writers and relevant information for effective assisted writing. Preliminary experiments show that WriteAhead2 has the potential to induce better writing and improve writing skills.

D19: A Concrete Chinese NLP Pipeline, by Nanyun Peng, Francis Ferraro, Mo Yu, Nicholas Andrews, Jay DeYoung, Max Thomas, Matthew R. Gormley, Travis Wolfe, Craig Harman, Benjamin Van Durme and Mark Dredze

Natural language processing research increasingly relies on the output of a variety of syntactic and semantic analytics. Yet integrating output from multiple analytics into a single framework can be time consuming and slow research progress. We present a Chinese Concrete NLP Pipeline: an NLP stack built using a series of open source systems integrated based on the Concrete data schema. Our pipeline includes data ingest, word segmentation, part of speech tagging, parsing, named entity recognition, relation extraction and cross document coreference resolution. Additionally, we integrate a tool for visualizing these annotations as well as allowing for the manual annotation of new data. We release our pipeline to the research community to facilitate work on Chinese language tasks that require rich linguistic annotations.

D28: Enhancing Instructor-Student and Student-Student Interactions with Mobile Interfaces and Summarization, by Wencan Luo, Xiangmin Fan, Muhsin Menekse, Jingtao Wang and Diane Litman

Educational research has demonstrated that asking students to respond to reflection prompts can increase interaction between instructors and students, which in turn can improve both teaching and learning especially in large classrooms. However, administering an instructor's prompts, collecting the students' responses, and summarizing these responses for both instructors and students is challenging and expensive. To address these challenges, we have developed an application called CourseMIRROR (Mobile In-situ Reflections and Review with Optimized Rubrics). CourseMIRROR uses a mobile interface to administer prompts and collect reflective responses for a set of instructor-assigned course lectures. After collection, CourseMIRROR automatically summarizes the reflections with an extractive phrase summarization method, using a clustering algorithm to rank extracted phrases by student coverage. Finally, CourseMIRROR presents the phrase summary to both instructors and students to help them understand the difficulties and misunderstandings encountered.

D59: Visualizing Deep-Syntactic Parser Output, by Juan Soler-Company, Miguel Ballesteros, Bernd Bohnet, Simon Mille and Leo Wanner

``Deep-syntactic" dependency structures bridge the gap between the surface-syntactic structures as produced by state-of-the-art dependency parsers and semantic logical forms in that they abstract away from surface-syntactic idiosyncrasies, but still keep the linguistic structure of a sentence. They have thus a great potential for such downstream applications as machine translation and summarization. In this demo paper, we propose an online version of a deep-syntactic parser that outputs deep-syntactic structures from plain sentences and visualizes them using the Brat tool. Along with the deep-syntactic structures, the user can also inspect the visual presentation of the surface-syntactic structures that serve as input to the deep-syntactic parser and that are produced by the joint tagger and syntactic transition-based parser ran in the pipeline before the deep-syntactic parser.

D4: Lean Question Answering over Freebase from Scratch, by Xuchen Yao

For the task of question answering (QA) over Freebase on the WebQuestions dataset (Berant et al., 2013), we found that 85% of all questions (in the training set) can be directly answered via a single binary relation. Thus we turned this task into slot-filling for <question topic, relation, answer> tuples: predicting relations to get answers given a question’s topic. We design efficient data structures to identify question topics organically from 46 million Freebase topic names, without employing any NLP processing tools. Then we present a lean QA system that runs in real time (in offline batch testing it answered two thousand questions in 51 seconds on a laptop). The system also achieved 7.8% better F1 score (harmonic mean of average precision and recall) than the previous state of the art.

D23: Online Readability and Text Complexity Analysis with TextEvaluator, by Diane Napolitano, Kathleen Sheehan and Robert Mundkowsky

We have developed the TextEvaluator system for providing text complexity and Common Core-aligned readability information. Detailed text complexity information is provided by eight component scores, presented in such a way as to aid in the user’s understanding of the overall readability metric, which is provided as a holistic score on a scale of 100 to 2000. The user may select a targeted US grade level and receive additional analysis relative to it. This and other capabilities are accessible via a feature-rich front-end, located at

D21: CroVeWA: Crosslingual Vector-Based Writing Assistance, by Hubert Soyer, Goran Topić, Pontus Stenetorp and Akiko Aizawa

We present an interactive web-based writing assistance system that is based on recent advances in crosslingual compositional distributed semantics. Given queries in Japanese or English, our system can retrieve semantically related sentences from high quality English corpora. By employing crosslingually constrained vector space models to represent phrases, our system naturally sidesteps several difficulties that would arise from direct word-to-text matching, and is able to provide novel functionality like the visualization of semantic relationships between phrases interlingually and intralingually.

D38: Ckylark: A More Robust PCFG-LA Parser, by Yusuke Oda, Graham Neubig, Sakriani Sakti, Tomoki Toda and Satoshi Nakamura

This paper describes Ckylark, a PCFG-LA style phrase structure parser that is more robust than other parsers in the genre. PCFG-LA parsers are known to achieve highly competitive performance, but sometimes the parsing process fails completely, and no parses can be generated. Ckylark introduces three new techniques that prevent possible causes for parsing failure: outputting intermediate results when coarse-to-fine analysis fails, smoothing lexicon probabilities, and scaling probabilities to avoid underflow. An experiment shows that this allows millions of sentences can be parsed without any failures, in contrast to other publicly available PCFG-LA parsers. Ckylark is implemented in C++, and is available open-source under the LGPL license.


Poster session 2B: Short papers — Plaza Exhibits All


8: Why Read if You Can Scan? Trigger Scoping Strategy for Biographical Fact Extraction, by Dian Yu, Heng Ji, Sujian Li, Chin-Yew Lin

The rapid growth of information sources brings a unique challenge to biographical information extraction: how to find specific facts without having to read all the words. An effective solution is to follow the human scanning strategy which keeps a specific keyword in mind and searches within a specific scope. In this paper, we mimic a scanning process to extract biographical facts: we use event and relation triggers as keywords, identify their scopes and apply type constraints to extract answers within the scope of a trigger. Experiments demonstrate that our approach outperforms state-of-the-art methods up to 26% absolute gain in F-score without using any syntactic analysis or external knowledge bases.

30: Response-based Learning for Machine Translation of Open-domain Database Queries, by Carolin Haas and Stefan Riezler

Response-based learning allows to adapt a statistical machine translation (SMT) system to an extrinsic task by extracting supervision signals from task-specific feedback. In this paper, we elicit response signals for SMT adaptation by executing semantic parses of translated queries against the Freebase database. The challenge of our work lies in scaling semantic parsers to the lexical diversity of open-domain databases. We find that parser performance on incorrect English sentences, which is standardly ignored in parser evaluation, is key in model selection. In our experiments, the biggest improvements in F1-score for returning the correct answer from a semantic parse for a translated query are achieved by selecting a parser that is carefully enhanced by paraphrases and synonyms.

34: Lachmannian Archetype Reconstruction for Ancient Manuscript Corpora, by Armin Hoenen

Two goals are targeted by computer philology for ancient manuscript corpora: firstly, making an edition, that is roughly speaking one text version representing the whole corpus, which contains variety induced through copy errors and other processes and secondly, producing a stemma. A stemma is a graph-based visualization of the copy history with manuscripts as nodes and copy events as edges. Its root, the so-called archetype, is the supposed original text or urtext from which all subsequent copies are made. Our main contribution is to present one of the first computational approaches to automatic archetype reconstruction and to introduce the first text-based evaluation for automatically produced archetypes. We compare a philologically generated archetype with one generated by bio-informatic software.

122: Multi-Task Word Alignment Triangulation for Low-Resource Languages, by Tomer Levinboim and David Chiang

We present a multi-task learning approach that jointly trains three word alignment models over disjoint bitexts of three languages

- source, target and pivot. Our approach builds upon model triangulation, following Wang et al., which approximates a source-target model by combining source-pivot and pivot-target models. We develop a MAP-EM algorithm that uses triangulation as a prior, and show how to extend it to a multi-task setting. On a low-resource Czech-English corpus, using French as the pivot, our multi-task learning approach more than doubles the gains in both F- and BLEU scores compared to the interpolation approach of Wang et al. Further experiments reveal that the choice of pivot language does not significantly effect performance.

126: Learning to parse with IAA-weighted loss, by Héctor Martínez Alonso, Barbara Plank, Arne Skjærholt, Anders Søgaard

Natural language processing (NLP) annotation projects employ guidelines to maximize inter-annotator agreement (IAA), and models are estimated assuming that there is one single ground truth. However, not all disagreement is noise, and in fact some of it may contain valuable linguistic information. We integrate such information in the training of a cost-sensitive dependency parser. We introduce five different factorizations of IAA and the corresponding loss functions, and evaluate these across six different languages. We obtain robust improvements across the board using a factorization that considers dependency labels and directionality. The best method-dataset combination reaches an average overall error reduction of 6.4% in labeled attachment score.

142: Automatic cognate identification with gap-weighted string subsequences., by Taraka Rama

In this paper, we describe the problem of cognate identification in NLP. We introduce the idea of gap-weighted subsequences for discriminating cognates from non-cognates. We also propose a scheme to integrate phonetic features into the feature vectors for cognate identification. We show that subsequence based features perform better than state-of-the-art classifier for the purpose of cognate identification. The contribution of this paper is the use of subsequence features for cognate identification.

148: Short Text Understanding by Leveraging Knowledge into Topic Model, by Shansong Yang, Weiming Lu, Dezhi Yang, Liang Yao, Baogang Wei

In this paper, we investigate the challenging task of understanding short text (STU task) by jointly considering topic modeling and knowledge incorporation. Knowledge incorporation can solve the content sparsity problem effectively for topic modeling. Specifically, the phrase topic model is proposed to leverage the auto-mined knowledge, i.e., the phrases, to guide the generative process of short text. Experimental results illustrate the effectiveness of the mechanism that utilizes knowledge to improve topic modeling’s performance.

158: Discriminative Phrase Embedding for Paraphrase Identification, by Wenpeng Yin and Hinrich Schütze

This work, concerning paraphrase identification task, on one hand contributes to expanding deep learning embeddings to include continuous and discontinuous linguistic phrases. On the other hand, it comes up with a new scheme TF-KLD-KNN to learn the discriminative weights of words and phrases specific to paraphrase task, so that a weighted sum of embeddings can represent sentences more effectively. Based on these two innovations we get competitive state-of-the-art performance on paraphrase identification.

206: Combining Word Embeddings and Feature Embeddings for Fine-grained Relation Extraction, by Mo Yu, Matthew R. Gormley, Mark Dredze

Compositional embedding models build a representation for a linguistic structure based on its component word embeddings. While recent work has combined these word embeddings with hand crafted features for improved performance, they are limited to using a small number of features due to model complexity, thus limiting their applicability. We propose a new model that conjoins features and word embeddings while maintaing a small number of parameters by learning feature embeddings jointly with the parameters of a compositional model. The result is a method that can scale to more features and more labels, which avoiding over-fitting. We demonstrate that our model attains state-of-the-art results on ACE and ERE fine-grain relation extraction.

224: LR Parsing for LCFRS, by Laura Kallmeyer and Wolfgang Maier

LR parsing is a popular parsing strategy for variants of Context-Free Grammar (CFG). It has also been used for mildly context-sensitive formalisms, such as Tree-Adjoining Grammar. In this paper, we present the first LR-style parsing algorithm for Linear Context-Free Rewriting Systems (LCFRS), a mildly context-sensitive extension of CFG which has received considerable attention in the last years.

228: Simple task-specific bilingual word embeddings, by Stephan Gouws and Anders Søgaard

We introduce a simple wrapper method that uses off-the-shelf word embedding algorithms to learn task-specific bilingual word embeddings. We use a small dictionary to produce mixed context-target pairs that we use to train embedding models. The model has the advantage that it (a) is independent of the choice of embedding algorithm, (b) does not require parallel data, and (c) can be adapted to specific tasks by re-defining the equivalence classes. We show how our method outperforms off-the-shelf bilingual embeddings on the task of unsupervised cross-language part-of-speech (POS) tagging, as well as on the task of semi-supervised cross-language super sense (SuS) tagging.

272: Sampling Techniques for Streaming Cross Document Coreference Resolution, by Luke Shrimpton, Victor Lavrenko, Miles Osborne

We present the first truly streaming cross document coreference resolution (CDC) system. Processing infinite streams of mentions forces us to use a constant amount of memory and so we maintain a representative, fixed sized sample at all times. For the sample to be representative it should represent a large number of entities whilst taking into account both temporal recency and distant references. We introduce new sampling techniques that take into account a notion of streaming discourse (current mentions depend on previous mentions). Using the proposed sampling techniques we are able to get a CEAFe score within 5% of a non-streaming system while using only 30% of the memory.

282: Clustering Sentences with Density Peaks for Multi-document Summarization, by Yang Zhang, Yunqing Xia, Yi Liu, Wenmin Wang

Multi-document Summarization (MDS) is of great value to many real world applications. Many scoring models are proposed to select appropriate sentences from documents to form the summary, in which the clusterbased methods are popular. In this work, we propose a unified sentence scoring model which measures representativeness and diversity at the same time. Experimental results on DUC04 demonstrate that our MDS method outperforms the DUC04 best method and the existing cluster-based methods, and it yields close results compared to the state-of-the-art generic MDS methods. Advantages of the proposed MDS method are two-fold: (1) The density peaks clustering algorithm is adopted, which is effective and fast. (2) No external resources such as Wordnet and Wikipedia or complex language parsing algorithms is used, making reproduction and deployment very easy in real environment.

338: Large-Scale Native Language Identification with Cross-Corpus Evaluation, by Shervin Malmasi and Mark Dras

We present a large-scale Native Language Identification (NLI) experiment on new data, with a focus on cross-corpus evaluation to identify corpus- and genre-independent language transfer features. We test a new corpus and show it is comparable to other NLI corpora and suitable for this task. Cross-corpus evaluation on two large corpora achieves good accuracy and evidences the existence of reliable language transfer features, but lower performance also suggests that NLI models are not completely portable across corpora. Finally, we present a brief case study of features distinguishing Japanese learners' English writing, demonstrating the presence of cross-corpus and cross-genre language transfer features that are highly applicable to SLA and ESL research.

384: Unsupervised Sparse Vector Densification for Short Text Similarity, by Yangqiu Song and Dan Roth

Sparse representations of text such as bag-of-words models or extended explicit semantic analysis (ESA) representations are commonly used in many NLP applications. However, for short texts, the similarity between two such sparse vectors is not accurate due to the small term overlap. While there have been multiple proposals for dense representations of words, measuring similarity between short texts (sentences, snippets, paragraphs) requires combining these token level similarities. In this paper, we propose to combine ESA representations and word2vec representations as a way to generate denser representations and, consequently, a better similarity measure between short texts. We study three densification mechanisms that involve aligning sparse representation via many-to-many, many-to-one, and one-to-one mappings. We then show the effectiveness of these mechanisms on measuring similarity between short texts.

426: #WhyIStayed, #WhyILeft: Microblogging to Make Sense of Domestic Abuse, by Nicolas Schrading, Cecilia Ovesdotter Alm, Raymond Ptucha, Christopher Homan

In September 2014, Twitter users unequivocally reacted to the Ray Rice assault scandal by unleashing personal stories of domestic abuse via the hashtags #WhyIStayed or #WhyILeft. We explore at a macro-level firsthand accounts of domestic abuse from a substantial, balanced corpus of tweeted instances designated with these tags. To seek insights into the reasons victims give for staying in vs. leaving abusive relationships, we analyze the corpus using linguistically motivated methods. We also report on an annotation study for corpus assessment. We perform classification, contributing a classifier that discriminates between the two hashtags exceptionally well at 82% accuracy with a substantial error reduction over its baseline.

444: Morphological Word-Embeddings, by Ryan Cotterell and Hinrich Schütze

Linguistic similarity is multi-faceted. For instance, two words may be similar with respect to semantics, syntax, or morphology inter alia. Continuous word-embeddings have been shown to capture most of these shades of similarity to some degree. This work considers guiding word-embeddings with morphologically annotated data, a form of semi-supervised learning, encouraging the vectors to encode a word’s morphology, i.e., words close in the embedded space share morphological features. We extend the log-bilinear model to this end and show that indeed our learned embeddings achieve this, using German as a case study.

458: Recognizing Social Constructs from Textual Conversation, by Somak Aditya, Chitta Baral, Nguyen Ha Vo, Joohyung Lee, Jieping Ye, Zaw Naung, Barry Lumpkin, Jenny Hastings, Richard Scherl, Dawn M. Sweet, Daniela Inclezan

In this paper we present our work on recognizing high level social constructs such as Leadership and Status from textual conversation using an approach that makes use of the background knowledge about social hierarchy and integrates statistical methods and symbolic logic based methods. We use a stratified approach in which we first detect lower level language constructs such as politeness, command and agreement that help us to infer intermediate constructs such as deference, closeness and authority that are observed between the parties engaged in conversation. These intermediate constructs in turn are used to determine the social constructs Leadership and Status. We have implemented this system successfully in both English and Korean languages and achieved considerable accuracy.

468: Two/Too Simple Adaptations of Word2Vec for Syntax Problems, by Wang Ling, Chris Dyer, Alan W Black, Isabel Trancoso

We present two simple modifications to the models in the popular Word2Vec tool, in order to generate embeddings more suited to tasks involving syntax. The main issue with the original models is the fact that they are insensitive to word order. While order independence is useful for inducing semantic representations, this leads to suboptimal results when they are used to solve syntax-based problems. We show improvements in part-of-speech tagging and dependency parsing using our proposed models.

488: Random Walks and Neural Network Language Models on Knowledge Bases, by Josu Goikoetxea, Aitor Soroa, Eneko Agirre

Random walks over large knowledge bases like WordNet have been successfully used in word similarity, relatedness and disambiguation tasks. Unfortunately, those algorithms are relatively slow for large repositories, with significant memory footprints. In this paper we present a novel algorithm which encodes the structure of a knowledge base in a continuous vector space, combining random walks and neural net language models in order to produce novel word representations. Evaluation in word relatedness and similarity datasets yields equal or better results than those of a random walk algorithm, using a dense representation (300 dimensions instead of 117K). Furthermore, the word representations are complementary to those of the random walk algorithm and to corpus-based continuous representations, improving the state-of-the-art in the similarity dataset. Our technique opens up exciting opportunities to combine distributional and knowledge-based word representations.

492: Estimating Numerical Attributes by Bringing Together Fragmentary Clues, by Hiroya Takamura and Jun'ichi Tsujii

This work is an attempt to automatically obtain numerical attributes of physical objects. We propose to represent each physical object as a feature vector and represent sizes as linear functions of feature vectors. We train the function in the framework of the combined regression and ranking with many types of fragmentary clues including absolute clues (e.g., A is 30cm long) and relative clues (e.g., A is larger than B).

534: Unsupervised POS Induction with Word Embeddings, by Chu-Cheng Lin, Waleed Ammar, Chris Dyer, Lori Levin

Unsupervised word embeddings have been shown to be valuable as features in supervised learning problems; however, their role in unsupervised problems has been less thoroughly explored. In this paper, we show that embeddings can likewise add value to the problem of unsupervised POS induction. In two representative models of POS induction, we replace multinomial distributions over the vocabulary with multivariate Gaussian distributions over word embeddings and observe consistent improvements in eight languages. We also analyze the effect of various choices while inducing word embeddings on "downstream" POS induction results.

642: Extracting Information about Medication Use from Veterinary Discussions, by Haibo Ding and Ellen Riloff

Our research aims to extract information about medication use from veterinary discussion forums. We introduce the task of categorizing information about medication use to determine whether a doctor has prescribed medication, changed protocols, observed effects, or stopped use of a medication. First, we create a medication detector for informal veterinary texts and show that features derived from the Web can be very powerful. Second, we create classifiers to categorize each medication mention with respect to six categories. We demonstrate that this task benefits from a rich linguistic feature set, domain-specific semantic features produced by a weakly supervised semantic tagger, and balanced self-training.

650: MPQA 3.0: An Entity/Event-Level Sentiment Corpus, by Lingjia Deng and Janyce Wiebe

This paper presents an annotation scheme for adding entity and event target annotations to the MPQA corpus, a rich span-annotated opinion corpus. The new corpus promises to be a valuable new resource for developing systems for entity/event-level sentiment analysis. Such systems, in turn, would be valuable in NLP applications such as Automatic Question Answering. We introduce the idea of entity and event targets (eTargets), describe the annotation scheme, and present the results of an agreement study.

706: GPU-Friendly Local Regression for Voice Conversion, by Taylor Berg-Kirkpatrick and Dan Klein

Voice conversion is the task of transforming a source speaker's voice so that it sounds like a target speaker's voice. We present a GPU-friendly local regression model for voice conversion that is capable of converting speech in real-time and achieves state-of-the-art accuracy on this task. Our model uses a new approximation for computing local regression coefficients that is explicitly designed to preserve memory locality. As a result, our inference procedure is amenable to efficient implementation on the GPU. Our approach is more than 10X faster than a highly optimized CPU-based implementation, and is able to convert speech 2.7X faster than real-time.

Wednesday, June 3


Registration and Breakfast


Invited Talk by Fei-fei Li: A Quest for Visual Intelligence in Computers — Plaza Ballroom A, B & C

Chair: Mirella Lapata, University of Edinburgh

More than half of the human brain is involved in visual processing. While it took mother nature billions of years to evolve and deliver us a remarkable human visual system, computer vision is one of the youngest disciplines of AI, born with the goal of achieving one of the loftiest dreams of AI. The central problem of computer vision is to turn millions of pixels of a single image into interpretable and actionable concepts so that computers can understand pictures just as well as humans do, from objects, to scenes, activities, events and beyond. Such technology will have a fundamental impact in almost every aspect of our daily life and the society as a whole, ranging from e-commerce, image search and indexing, assistive technology, autonomous driving, digital health and medicine, surveillance, national security, robotics and beyond. In this talk, I will give an overview of what computer vision technology is about and its brief history. I will then discuss some of the recent work from my lab towards large scale object recognition and visual scene story telling. I will particularly emphasize on what we call the "three pillars" of AI in our quest for visual intelligence: data, learning and knowledge. Each of them is critical towards the final solution, yet dependent on the other. This talk draws upon a number of projects ongoing at the Stanford Vision Lab.




8A: NLP for Web, Social Media and Social Sciences (Long + TACL Papers) — Plaza Ballroom A & B

Chair: Philip Resnik, University of Maryland

8B: Language and Vision (Long + TACL Papers) — Plaza Ballroom D & E

Chair: Yoav Artzi, University of Washington

8C: Machine Translation (Long + TACL Papers) — Plaza Ballroom F

Chair: Haitao Mi, IBM Research


351: Testing and Comparing Computational Approaches for Identifying the Language of Framing in Political News, by Eric Baumer, Elisha Elovic, Ying Qin, Francesca Polletta, Geri Gay

The subconscious influence of framing on perceptions of political issues is well-document in political science and communication research. A related line of work suggests that drawing attention to framing may help reduce such framing effects by enabling frame reflection, critical examination of the framing underlying an issue. However, definite guidance on how to identify framing does not exist. This paper presents a technique for identifying frame-invoking language. The paper first describes a human subjects pilot study that explores how individuals identify framing and informs the design of our technique. The paper then describes our data collection and annotation approach. Results show that the best performing classifiers achieve performance comparable to that of human annotators, and they indicate which aspects of language most pertain to framing. Both technical and theoretical implications are discussed.

539: Translating Videos to Natural Language Using Deep Recurrent Neural Networks, by Subhashini Venugopalan, Huijuan Xu, Jeff Donahue, Marcus Rohrbach, Raymond Mooney, Kate Saenko

Solving the visual symbol grounding problem has long been a goal of artificial intelligence. The field appears to be advancing closer to this goal with recent breakthroughs in deep learning for natural language grounding in static images. In this paper, we propose to translate videos directly to sentences using a unified deep neural network with both convolutional and recurrent structure. Described video datasets are scarce, and most existing methods have been applied to toy domains with a small vocabulary of possible words. By transferring knowledge from 1.2M+ images with category labels and 100,000+ images with captions, our method is able to create sentence descriptions of open-domain videos with large vocabularies. We compare our approach with recent work using language generation metrics, subject, verb, and object prediction accuracy, and a human evaluation.

44: A Comparison of Update Strategies for Large-Scale Maximum Expected BLEU Training, by Joern Wuebker, Sebastian Muehr, Patrick Lehnen, Stephan Peitz, Hermann Ney

This work presents a flexible and efficient discriminative training approach for statistical machine translation. We propose to use the RPROP algorithm for optimizing a maximum expected BLEU objective and experimentally compare it to several other updating schemes. It proves to be more efficient and effective than the previously proposed growth transformation technique and also yields better results than stochastic gradient descent and AdaGrad. We also report strong empirical results on two large scale tasks, namely BOLT Chinese->English and WMT German->English, where our final systems outperform results reported by Setiawan and Zhou (2013) and on On the WMT task, discriminative training is performed on the full training data of 4M sentence pairs, which is unsurpassed in the literature.


TACL-498: Extracting Lexically Divergent Paraphrases from Twitter, by Wei Xu, Alan Ritter, Chris Callison-Burch, William B. Dolan, Yangfeng Ji

We present MultiP (Multi-instance Learning Paraphrase Model), a new model suited to identify paraphrases within the short messages on Twitter. We jointly model paraphrase relations between word and sentence pairs and assume only sentence-level annotations during learning. Using this principled latent variable model alone, we achieve the performance competitive with a state-of-the-art method which combines a latent space model with a feature-based supervised classifier. Our model also captures lexically divergent paraphrases that differ from yet complement previous methods; combining our model with previous work significantly outperforms the state-of-the-art. In addition, we present a novel annotation methodology that has allowed us to crowdsource a paraphrase corpus from Twitter. We make this new dataset available to the research community.

TACL-276: A Bayesian Model of Grounded Color Semantics, by Brian McMahan and Matthew Stone

Natural language meanings allow speakers to encode important real-world distinctions, but corpora of grounded language use also reveal that speakers categorize the world in different ways and describe situations with different terminology. To learn meanings from data, we therefore need to link underlying representations of meaning to models of speaker judgment and speaker choice. This paper describes a new approach to this problem: we model variability through uncertainty in categorization boundaries and distributions over preferred vocabulary. We apply the approach to a large data set of color descriptions, where statistical evaluation documents its accuracy. The results are available as a Lexicon of Uncertain Color Standards (LUX), which supports future efforts in grounded language understanding and generation by probabilistically mapping 829 English color descriptions to potentially context-sensitive regions in HSV color space.

TACL-555: Gappy Pattern Matching on GPUs for On-Demand Extraction of Hierarchical Translation Grammars, by Hua He, Jimmy Lin, Adam Lopez

Grammars for machine translation can be materialized on demand by finding source phrases in an indexed parallel corpus and extracting their translations. This approach is limited in practical applications by the computational expense of online lookup and extraction. For phrase-based models, recent work has shown that on-demand grammar extraction can be greatly accelerated by parallelization on general purpose graphics processing units (GPUs), but these algorithms do not work for hierarchical models, which require matching patterns that contain gaps. We address this limitation by presenting a novel GPU algorithm for on-demand hierarchical grammar extraction that is at least an order of magnitude faster than a comparable CPU algorithm when processing large batches of sentences. In terms of end-to-end translation, with decoding on the CPU, we increase throughput by roughly two thirds on a standard MT evaluation dataset. The GPU necessary to achieve these improvements increases the cost of a server by about a third. We believe that GPU-based extraction of hierarchical grammars is an attractive proposition, particularly for MT applications that demand high throughput.


267: Echoes of Persuasion: The Effect of Euphony in Persuasive Communication, by Marco Guerini, Gözde Özbal, Carlo Strapparava

While the effect of various lexical, syntactic, semantic and stylistic features have been addressed in persuasive language from a computational point of view, the persuasive effect of phonetics has received little attention. By modeling a notion of euphony and analyzing four datasets comprising persuasive and non-persuasive sentences in different domains (political speeches, movie quotes, slogans and tweets), we explore the impact of sounds on different forms of persuasiveness. We conduct a series of analyses and prediction experiments within and across datasets. Our results highlight the positive role of phonetic devices on persuasion.

238: Learning to Interpret and Describe Abstract Scenes, by Luis Gilberto Mateos Ortiz, Clemens Wolff, Mirella Lapata

Given a (static) scene, a human can effortlessly describe what is going on (who is doing what to whom, how, and why). The process requires knowledge about the world, how it is perceived, and described. In this paper we study the problem of interpreting and verbalizing visual information using abstract scenes created from collections of clip art images. We propose a model inspired by machine translation operating over a large parallel corpus of visual relations and linguistic descriptions. We demonstrate that this approach produces human-like scene descriptions which are both fluent and relevant, outperforming a number of competitive alternatives based on templates and sentence-based retrieval.

496: Learning Translation Models from Monolingual Continuous Representations, by Kai Zhao, Hany Hassan, Michael Auli

Translation models often fail to generate good translations for infrequent words or phrases. Previous work attacked this problem by inducing new translation rules from monolingual data with a semi-supervised algorithm. However, this approach does not scale very well since it is very computationally expensive to generate new translation rules for only a few thousand sentences. We propose a much faster and simpler method that directly hallucinates translation rules for infrequent phrases based on phrases with similar continuous representations for which a translation is known. To speed up the retrieval of similar phrases, we investigate approximated nearest neighbor search with redundant bit vectors which we find to be three times faster and significantly more accurate than locality sensitive hashing. Our approach of learning new translation rules improves a phrase-based baseline by up to 1.6 BLEU on Arabic-English translation, it is three-orders of magnitudes faster than existing semi-supervised methods and 0.5 BLEU more accurate.




NAACL Business Meeting — Plaza Ballroom A, B & C

Chair: Hal Daume III, University of Maryland


9A: Lexical Semantics and Sentiment Analysis (Long Papers) — Plaza Ballroom A & B

Chair: Saif Mohammad, National Research Council Canada

9B: NLP-enabled Technology (Long + TACL Papers) — Plaza Ballroom D & E

Chair: Brendan O'Connor, Univ. of Massachusetts, Amherst

9C: Linguistic and Psycholinguistic Aspects of CL (Long Papers) — Plaza Ballroom F

Chair: William Schuler, The Ohio State University


401: A Corpus and Model Integrating Multiword Expressions and Supersenses, by Nathan Schneider and Noah A. Smith

This paper introduces a task of identifying and semantically classifying lexical expressions in context. We investigate the online reviews genre, adding semantic supersense annotations to a 55,000 word English corpus that was previously annotated for multiword expressions. The noun and verb supersenses apply to full lexical expressions, whether single- or multiword. We then present a sequence tagging model that jointly infers lexical expressions and their supersenses. Results show that even with our relatively small training corpus in a noisy domain, the joint task can be performed to attain 70% class labeling F1.

506: How to Memorize a Random 60-Bit String, by Marjan Ghazvininejad and Kevin Knight

User-generated passwords tend to be memorable, but not secure. A random, computer-generated 60-bit string is much more secure. However, users cannot memorize random 60-bit strings. In this paper, we investigate methods for converting arbitrary bit strings into English word sequences (both prose and poetry), and we study their memorability and other properties.

261: A Bayesian Model for Joint Learning of Categories and their Features, by Lea Frermann and Mirella Lapata

Categories such as ANIMAL or FURNITURE are acquired at an early age and play an important role in processing, organizing, and conveying world knowledge. Theories of categorization largely agree that categories are characterized by features such as function or appearance and that feature and category acquisition go hand-in-hand, however previous work has considered these problems in isolation. We present the first model that jointly learns categories and their features. The set of features is shared across categories, and strength of association is inferred in a Bayesian framework. We approximate the learning environment with natural language text which allows us to evaluate performance on a large scale. Compared to highly engineered pattern-based approaches, our model is cognitively motivated, knowledge-lean, and learns categories and features which are perceived by humans as more meaningful.


375: Good News or Bad News: Using Affect Control Theory to Analyze Readers' Reaction Towards News Articles, by Areej Alhothali and Jesse Hoey

This paper proposes a novel approach to sentiment analysis that leverages work in sociology on symbolic interactionism. The proposed approach uses Affect Control Theory (ACT) to analyze readers' sentiment towards factual (objective) content and towards its entities (subject and object). ACT is a theory of affective reasoning that uses empirically derived equations to predict the sentiments and emotions that arise from events. This theory relies on several large lexicons of words with affective ratings in a three-dimensional space of evaluation, potency, and activity (EPA). The equations and lexicons of ACT were evaluated on a newly collected news-headlines corpus. ACT lexicon was expanded using a label propagation algorithm, resulting in 86,604 new words. The predicted emotions for each news headline was then computed using the augmented lexicon and ACT equations. The results had a precision of 82%, 79%, and 68% towards the event, the subject, and object, respectively. These results are significantly higher than those of standard sentiment analysis techniques.

TACL-384: Building a State-of-the-Art Grammatical Error Correction System, by Alla Rozovskaya and Dan Roth

This paper identifies and examines the key principles underlying building a state-of-the-art grammatical error correction system. We do this by analyzing the Illinois system that placed first among seventeen teams in the recent CoNLL-2013 shared task on grammatical error correction.

666: Shared common ground influences information density in microblog texts, by Gabriel Doyle and Michael Frank

If speakers use language rationally, they should structure their messages to achieve approximately uniform information density (UID), in order to optimize transmission via a noisy channel. Previous work identified a consistent increase in linguistic information across sentences in text as a signature of the UID hypothesis. This increase was derived from a predicted increase in context, but the context itself was not quantified. We use microblog texts from Twitter, tied to a single shared event (the baseball World Series), to quantify both linguistic and non-linguistic context. By tracking changes in contextual information, we predict and identify gradual and rapid changes in information content in response to in-game events. These findings lend further support to the UID hypothesis and highlights the importance of non-linguistic common ground for language production and processing.


592: Do We Really Need Lexical Information? Towards a Top-down Approach to Sentiment Analysis of Product Reviews, by Yulia Otmakhova and Hyopil Shin

Most of the current approaches to sentiment analysis of product reviews are dependent on lexical sentiment information and proceed in a bottom-up way, adding new layers of features to lexical data. In this paper, we maintain that a typical product review is not a bag of sentiments, but a narrative with an underlying structure and reoccurring patterns, which allows us to predict its sentiments knowing only its general polarity and discourse cues that occur in it. We hypothesize that knowing only the review’s score and its discourse patterns would allow us to accurately predict the sentiments of its individual sentences. The experiments we conducted prove this hypothesis and show a substantial improvement over the lexical baseline.

TACL-414: Predicting the Difficulty of Language Proficiency Tests, by Lisa Beinborn, Torsten Zesch, Iryna Gurevych

Language proficiency tests are used to evaluate and compare the progress of language learners. We present an approach for automatic difficulty prediction of C-tests that performs on par with human experts. On the basis of detailed analysis of newly collected data, we develop a model for C-test difficulty introducing four dimensions: solution difficulty, candidate ambiguity, inter-gap dependency, and paragraph difficulty. We show that cues from all four dimensions contribute to C-test difficulty.

454: Hierarchic syntax improves reading time prediction, by Marten van Schijndel and William Schuler

Previous work has debated whether humans make use of hierarchic syntax when processing language (Frank and Bod, 2011; Fossum and Levy, 2012). This paper uses an eye-tracking corpus to demonstrate that hierarchic syntax significantly improves reading time prediction over a strong n-gram baseline. This study shows that an interpolated 5-gram baseline can be made stronger by combining n-gram statistics over entire eye-tracking regions rather than simply using the last n-gram in each region, but basic hierarchic syntactic measures are still able to achieve significant improvements over this improved baseline.




Best Paper Plenary Session — Plaza Ballroom A, B & C

Chair: Claire Cardie, Cornell University


76: Retrofitting Word Vectors to Semantic Lexicons, by Manaal Faruqui, Jesse Dodge, Sujay Kumar Jauhar, Chris Dyer, Eduard Hovy, Noah A. Smith

Vector space word representations are learned from distributional information of words in large corpora. Although such statistics are semantically informative, they disregard the valuable information that is contained in semantic lexicons such as WordNet, FrameNet, and the Paraphrase Database. This paper proposes a method for refining vector space representations using relational information from semantic lexicons by encouraging linked words to have similar vector representations, and it makes no assumptions about how the input vectors were constructed. Evaluated on a battery of standard lexical semantic evaluation tasks in several languages, we obtain substantial improvements starting with a variety of word vector models. Our refinement method outperforms prior techniques for incorporating semantic lexicons into the word vector training algorithms.


450: “You’re Mr. Lebowski, I’m the Dude”: Inducing Address Term Formality in Signed Social Networks, by Vinodh Krishnan and Jacob Eisenstein

We present an unsupervised model for inducing signed social networks from the content exchanged across network edges. Inference in this model solves three problems simultaneously: (1) identifying the sign of each edge; (2) characterizing the distribution over content for each edge type; (3) estimating weights for triadic features that map to theoretical models such as structural balance. We apply this model to the problem of inducing the social function of address terms, such as Madame, comrade, and dude. On a dataset of movie scripts, our system obtains a coherent clustering of address terms, while at the same time making intuitively plausible judgments of the formality of social relations in each film. As an additional contribution, we provide a bootstrapping technique for identifying and tagging address terms in dialogue.


100: Unsupervised Morphology Induction Using Word Embeddings, by Radu Soricut and Franz Och

We present a language agnostic, unsupervised method for inducing morphological transformations between words. The method relies on certain regularities manifest in high-dimensional vector spaces. We show that this method is capable of discovering a wide range of morphological rules, which in turn are used to build morphological analyzers. We evaluate this method across six different languages and nine datasets, and show significant improvements across all languages.


Best paper awards and Closing Remarks