[T1] English Resource Semantics Location: Executive 3AB

[T2] Multilingual Multimodal Language Processing Using Neural Networks Location: Spinnaker

[T3] Question Answering with Knowledge Base, Web and Beyond Location: Marina 3

[T4] Recent Progress in Deep Learning for NLP Location: Spinnaker

[T5] Scalable Statistical Relational Learning for NLP Location: Marina 3

[T6] Statistical Machine Translation between Related Languages Location: Executive 3AB

How Can NLP Help Cure Cancer?

Cancer inflicts a heavy toll on our society. One out of seven women will be diagnosed with breast cancer during their lifetime, a fraction of them contributing to about 450,000 deaths annually worldwide. Despite billions of dollars invested in cancer research, our understanding of the disease, treatment, and prevention is still limited.

Majority of cancer research today takes place in biology and medicine. Computer science plays a minor supporting role in this process if at all. In this talk, I hope to convince you that NLP as a field has a chance to play a significant role in this battle. Indeed, free-form text remains the primary means by which physicians record their observations and clinical findings. Unfortunately, this rich source of textual information is severely underutilized by predictive models in oncology. Current models rely primarily only on structured data.

In the first part of my talk, I will describe a number of tasks where NLP-based models can make a difference in clinical practice. For example, these include improving models of disease progression, preventing over-treatment, and narrowing down to the cure. This part of the talk draws on active collaborations with oncologists from Massachusetts General Hospital (MGH).

In the second part of the talk, I will push beyond standard tools, introducing new functionalities and avoiding annotation-hungry training paradigms ill-suited for clinical practice. In particular, I will focus on interpretable neural models that provide rationales underlying their predictions, and semi-supervised methods for information extraction.

Chair: Joel Tetrault

Prior to the poster session, TACL and long-paper poster presenters will be given one minute each to pitch their paper. The poster session will immediately follow these presentations along with a buffet dinner.

Main Conference

A Recurrent Neural Networks Approach for Estimating the Quality of Machine Translation Output Hyun Kim and Jong-Hyeok Lee

Agreement on Target-bidirectional Neural Machine Translation Lemao Liu, Masao Utiyama, Andrew Finch and Eiichiro Sumita

An Unsupervised Model of Orthographic Variation for Historical Document Transcription Dan Garrette and Hannah Alpert-Abrams

Bidirectional RNN for Medical Event Detection in Electronic Health Records Abhyuday Jagannatha and Hong Yu

Breaking the Closed World Assumption in Text Classification Geli Fei and Bing Liu

Building Chinese Affective Resources in Valence-Arousal Dimensions Liang-Chih Yu, Lung-Hao Lee, Shuai Hao, Jin Wang, Yunchao He, Jun Hu, K. Robert Lai and Xuejie Zhang

Combining Recurrent and Convolutional Neural Networks for Relation Classification Ngoc Thang Vu, Heike Adel, Pankaj Gupta and Hinrich Schütze

Conversational Markers of Constructive Discussions Vlad Niculae and Cristian Danescu-Niculescu-Mizil

Cross-lingual Wikification Using Multilingual Embeddings Chen-Tse Tsai and Dan Roth

Deconstructing Complex Search Tasks: a Bayesian Nonparametric Approach for Extracting Sub-tasks Rishabh Mehrotra, Prasanta Bhattacharya and Emine Yilmaz

Expectation-Regulated Neural Model for Event Mention Extraction Ching-Yun Chang, Zhiyang Teng and Yue Zhang

Grammatical error correction using neural machine translation Zheng Yuan and Ted Briscoe

Improved Neural Network-based Multi-label Classification with Better Initialization Leveraging Label Co-occurrence Gakuto Kurata, Bing Xiang and Bowen Zhou

Improving event prediction by representing script participants Simon Ahrendt and Vera Demberg

Individual Variation in the Choice of Referential Form Thiago Castro Ferreira, Emiel Krahmer and Sander Wubben

Inferring Psycholinguistic Properties of Words Gustavo Paetzold and Lucia Specia

Intra-Topic Variability Normalization based on Linear Projection for Topic Classification Quan Liu, Wu Guo, Zhen-Hua Ling, Hui Jiang and Yu Hu

Joint Learning Templates and Slots for Event Schema Induction Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui and Zhifang Sui

Large-scale Multitask Learning for Machine Translation Quality Estimation Kashif Shah and Lucia Specia

Learning Distributed Word Representations For Bidirectional LSTM Recurrent Neural Network Peilu Wang, Yao Qian, Frank Soong, Lei He and Hai Zhao

Leverage Financial News to Predict Stock Price Movements Using Word Embeddings and Deep Neural Networks Yangtuo Peng and Hui Jiang

Multimodal Semantic Learning from Child-Directed Input Angeliki Lazaridou, Grzegorz Chrupała, Raquel Fernandez and Marco Baroni

Online Multilingual Topic Models with Multi-Level Hyperpriors Kriste Krstovski, David Smith and Michael J. Kurtz

Psycholinguistic Features for Deceptive Role Detection in Werewolf Codruta Girlea, Roxana Girju and Eyal Amir

Recurrent Support Vector Machines For Slot Tagging In Spoken Language Understanding Yangyang Shi, Kaisheng Yao, Hu Chen, Dong Yu, Yi-Cheng Pan and Mei-Yuh Hwang

STransE: a novel embedding model of entities and relationships in knowledge bases Dat Quoc Nguyen, Kairit Sirts, Lizhen Qu and Mark Johnson

Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks Ji Young Lee and Franck Dernoncourt

Shift-Reduce CCG Parsing using Neural Network Models Bharat Ram Ambati, Tejaswini Deoskar and Mark Steedman

Structured Prediction with Output Embeddings for Semantic Image Annotation Ariadna Quattoni, Arnau Ramisa, Pranava Swaroop Madhyastha, Edgar Simo-Serra and Francesc Moreno-Noguer

Symmetric Patterns and Coordinations: Fast and Enhanced Representations of Verbs and Adjectives Roy Schwartz, Roi Reichart and Ari Rappoport

The Sensitivity of Topic Coherence Evaluation to Topic Cardinality Jey Han Lau and Timothy Baldwin

Transition-Based Syntactic Linearization with Lookahead Features Ratish Puduppully, Yue Zhang and Manish Shrivastava

Vision and Feature Norms: Improving automatic feature norm learning through cross-modal maps Luana Bulat, Douwe Kiela and Stephen Clark

Student Research Workshop Papers

An End-to-end Approach to Learning Semantic Frames with Feedforward Neural Network Yukun Feng, Yipei Xu and Dong Yu

Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn't. Anna Gladkova, Aleksandr Drozd and Satoshi Matsuoka

Argument Identification in Chinese Editorials Marisa Chow

Automatic tagging and retrieval of E-Commerce products based on visual features Vasu Sharma and Harish Karnick

Combining syntactic patterns and Wikipedia's hierarchy of hyperlinks to extract relations: The case of meronymy extraction Debela Tesfaye Gemechu, Michael Zock and Solomon Teferra

Data-driven Paraphrasing and Stylistic Harmonization Gerold Hintz

Detecting 'Smart' Spammers on Social Network: A Topic Model Approach Linqing Liu, Yao Lu, Ye Luo, Renxian Zhang, Laurent Itti and Jianwei Lu

Developing language technology tools and resources for a resource-poor language: Sindhi Raveesh Motlani

System Demonstrations

rstWeb - A Browser-based Annotation Interface for Rhetorical Structure Theory and Discourse Relations Amir Zeldes

Instant Feedback for Increasing the Presence of Solutions in Peer Reviews Huy Nguyen, Wenting Xiong and Diane Litman

Farasa: A Fast and Furious Segmenter for Arabic Ahmed Abdelali, Kareem Darwish, Nadir Durrani and Hamdy Mubarak

iAppraise: A Manual Machine Translation Evaluation Environment Supporting Eye-tracking Ahmed Abdelali, Nadir Durrani and Francisco Guzmán

Linguistica 5: Unsupervised Learning of Linguistic Structure Jackson Lee and John Goldsmith

TransRead: Designing a Bilingual Reading Experience with Machine Translation Technologies François Yvon, Yong Xu, Marianna Apidianaki, Clément Pillias and Pierre Cubaud

New Dimensions in Testimony Demonstration Ron Artstein, Alesia Gainer, Kallirroi Georgila, Anton Leuski, Ari Shapiro and David Traum

ArgRewrite: A Web-based Revision Assistant for Argumentative Writings Fan Zhang, Rebecca Hwa, Diane Litman and Homa B. Hashemi

Scaling Up Word Clustering Jon Dehdari, Liling Tan and Josef van Genabith

Task Completion Platform: A self-serve multi-domain goal oriented dialogue platform Paul Crook, Alex Marin, Vipul Agarwal, Khushboo Aggarwal, Tasos Anastasakos, Ravi Bikkula, Daniel Boies, Asli Celikyilmaz, Senthilkumar Chandramohan, Zhaleh Feizollahi, Roman Holenstein, Minwoo Jeong, Omar Khan, Young-Bum Kim, Elizabeth Krawczyk, Xiaohu Liu, Danko Panic, Vasiliy Radostev, Nikhil Ramesh, Jean-Phillipe Robichaud, Alexandre Rochette, Logan Stromberg and Ruhi Sarikaya

Moderator: Jason Eisner

Panelists: Kyunghyun Cho, Chris Dyer, Pascale Fung, Heng Ji

• What are the big problems in NLP historically, now, and in the future? (What do we need to solve, regardless of the approach for solving it?)
• What current NLP problems has DL solved, or where has DL made an important contribution towards improving the state of the art?
• Does DL guide NLP towards new problems? Do we already have examples? Do you want to speculate? (Have a new hammer, looking for un-hammered nails.)
• Does DL change our methodology profoundly, or is it just another machine learning method? Is there a greater danger of overfitting because of the massive tuning required? Given the computational requirements, are off-the-shelf tools incorporating DL practical?
• Is the use of off-the-shelf word embeddings the major contribution of DL? Does every task in which in the past we had bag of words features now required to also use word embedding features?
• Is linguistics obsolete because DL will find better representations on its own? Or should DL be combined with traditional representations of latent linguistic structure? What is the best way to do that – hybrid architectures, hybrid training objectives, hand-designed input representations, or something else?
• Is DL mostly good for supervised mapping of input to output where very large training sets are available? Or can it also help for semi-supervised learning and unsupervised structure discovery?
• What are the best approaches to interpretability (explaining why a DL system made a particular decision)? What are the best approaches to understanding the latent representations and figuring out what the system is missing and how to fix that?
• How much do architectures and parameters need to be task-specific? How much can researchers reuse architectures, and learning algorithms reuse parameters, across tasks?
• A DL design that looks nice on paper often doesn't work right away. What are best practices for achieving good performance? Do experienced researchers not have this problem because they know more tricks of the trade and have better intuitions about hyperparameters? Or does every paper involve 6 months of fiddling around on a dev set until it works? Is it worth doing automatic tuning of hyperparameters, e.g., Bayesian optimization?

Chair: Joel Tetrault

Prior to the poster session, TACL and long-paper poster presenters will be given one minute each to pitch their paper. The poster session will immediately follow these presentations along with a buffet dinner.

Main Conference

Assessing Relative Sentence Complexity using an Incremental CCG Parser Bharat Ram Ambati, Siva Reddy and Mark Steedman

Automatic Prediction of Linguistic Decline in Writings of Subjects with Degenerative Dementia Davy Weissenbacher, Travis A. Johnson, Laura Wojtulewicz, Amylou Dueck, Dona Locke, Richard Caselli and Graciela Gonzalez

Automatically Inferring Implicit Properties in Similes Ashequl Qadir, Ellen Riloff and Marilyn Walker

BIRA: Improved Predictive Exchange Word Clustering Jon Dehdari, Liling Tan and Josef van Genabith

Bootstrapping Translation Detection and Sentence Extraction from Comparable Corpora Kriste Krstovski and David Smith

Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks Matthew Francis-Landau, Greg Durrett and Dan Klein

Consensus Maximization Fusion of Probabilistic Information Extractors Miguel Rodriguez, Sean Goldberg and Daisy Zhe Wang

Cross-genre Event Extraction with Knowledge Enrichment Hao Li and Heng Ji

Deep Lexical Segmentation and Syntactic Parsing in the Easy-First Dependency Framework Matthieu Constant, Joseph Le Roux and Nadi Tomeh

Discriminative Reranking for Grammatical Error Correction with Statistical Machine Translation Tomoya Mizumoto and Yuji Matsumoto

Emergent: a novel data-set for stance classification William Ferreira and Andreas Vlachos

Eyes Don't Lie: Predicting Machine Translation Quality Using Eye Movement Hassan Sajjad, Francisco Guzmán, Nadir Durrani, Ahmed Abdelali, Houda Bouamor, Irina Temnikova and Stephan Vogel

Fast and Easy Short Answer Grading with High Accuracy Md Arafat Sultan, Cristobal Salazar and Tamara Sumner

Frustratingly Easy Cross-Lingual Transfer for Transition-Based Dependency Parsing Ophélie Lacroix, Lauriane Aufrant, Guillaume Wisniewski and François Yvon

Geolocation for Twitter: Timing Matters Mark Dredze, Miles Osborne and Prabhanjan Kambadur

Incorporating Side Information into Recurrent Neural Network Language Models Cong Duy Vu Hoang, Trevor Cohn and Gholamreza Haffari

Integrating Morphological Desegmentation into Phrase-based Decoding Mohammad Salameh, Colin Cherry and Grzegorz Kondrak

Interlocking Phrases in Phrase-based Statistical Machine Translation Ye Kyaw Thu, Andrew Finch and Eiichiro Sumita

K-Embeddings: Learning Conceptual Embeddings for Words using Context Thuy Vu and D. Stott Parker

Learning Composition Models for Phrase Embeddings Mo Yu and Mark Dredze

Learning a POS tagger for AAVE-like language Anna Jørgensen, Dirk Hovy and Anders Søgaard

Learning to Recognize Ancillary Information for Automatic Paraphrase Identification Simone Filice and Alessandro Moschitti

MAWPS: A Math Word Problem Repository Rik Koncel-Kedziorski, Subhro Roy, Aida Amini, Nate Kushman and Hannaneh Hajishirzi

Making Dependency Labeling Simple, Fast and Accurate Tianxiao Shen, Tao Lei and Regina Barzilay

PIC a Different Word: A Simple Model for Lexical Substitution in Context Stephen Roller and Katrin Erk

PRIMT: A Pick-Revise Framework for Interactive Machine Translation Shanbo Cheng, Shujian Huang, Huadong Chen, Xin-Yu Dai and Jiajun Chen

Patterns of Wisdom: Discourse-Level Style in Multi-Sentence Quotations Kyle Booten and Marti A. Hearst

Right-truncatable Neural Word Embeddings Jun Suzuki and Masaaki Nagata

Sentiment Composition of Words with Opposing Polarities Svetlana Kiritchenko and Saif Mohammad

Simple, Fast Noise-Contrastive Estimation for Large RNN Vocabularies Barret Zoph, Ashish Vaswani, Jonathan May and Kevin Knight

Sparse Bilingual Word Representations for Cross-lingual Lexical Entailment Yogarshi Vyas and Marine Carpuat

The Instantiation Discourse Relation: A Corpus Analysis of Its Properties and Improved Detection Junyi Jessy Li and Ani Nenkova

Visual Storytelling Ting-Hao Huang, Francis Ferraro, Nasrin Mostafazadeh, Ishan Misra, Jacob Devlin, Aishwarya Agrawal, Ross Girshick, Xiaodong He, Pushmeet Kohli, Dhruv Batra, Larry Zitnick, Devi Parikh, Lucy Vanderwende, Michel Galley and Margaret Mitchell

Student Research Workshop

Effects of Communicative Pressures on Novice L2 Learners' Use of Optional Formal Devices Yoav Binoun, Francesca Delogu, Clayton Greenberg, Mindaugas Mozuraitis and Matthew Crocker

Explicit Argument Identification for Discourse Parsing In Hindi: A Hybrid Pipeline Rohit Jain and Dipti Sharma

Exploring Fine-Grained Emotion Detection in Tweets Jasy Suet Yan Liew and Howard Turtle

Extraction of Bilingual Technical Terms for Chinese-Japanese Patent Translation Wei Yang, Jinghui Yan and Yves Lepage

Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter Zeerak Waseem and Dirk Hovy

Non-decreasing Sub-modular Function for Comprehensible Summarization Litton JKurisinkel, Pruthwik Mishra, Vigneshwaran Muralidaran, Vasudeva Varma and Dipti Misra Sharma

Phylogenetic simulations over constraint-based grammar formalisms Andrew Lamont and Jonathan Washington

Question Answering over Knowledge Base using Weakly Supervised Memory Networks Sarthak Jain

Using Related Languages to Enhance Statistical Language Models Anna Currey, Alina Karakanta and Jon Dehdari

System Demonstrations

Illinois Math Solver: Math Reasoning on the Web Subhro Roy and Dan Roth

LingoTurk: managing crowdsourced tasks for psycholinguistics Florian Pusse, Asad Sayeed and Vera Demberg

Sentential Paraphrasing as Black-Box Machine Translation Courtney Napoles, Chris Callison-Burch and Matt Post

A Tag-based English Math Word Problem Solver with Understanding, Reasoning and Explanation Chao-Chun Liang, Kuang-Yi Hsu, Chien-Tsung Huang, Chung-Min Li, Shen-Yu Miao and Keh-Yih Su

Cross-media Event Extraction and Recommendation Di Lu, Clare Voss, Fangbo Tao, Xiang Ren, Rachel Guan, Rostyslav Korolov, Tongtao Zhang, Dongang Wang, Hongzhi Li, Taylor Cassidy, Heng Ji, Shih-fu Chang, Jiawei Han, William Wallace, James Hendler, Mei Si and Lance Kaplan

SODA: Service Oriented Domain Adaptation Architecture for Microblog Categorization Himanshu Sharad Bhatt, Sandipan Dandapat, Peddamuthu Balaji, Shourya Roy, Sharmistha Jat and Deepali Semwal

Lecture Translator - Speech translation framework for simultaneous lecture translation Markus Müller, Thai Son Nguyen, Jan Niehues, Eunah Cho, Bastian Krüger, Thanh-Le Ha, Kevin Kilgour, Matthias Sperber, Mohammed Mediani, Sebastian Stüker and Alex Waibel

Zara The Supergirl: An Empathetic Personality Recognition System Pascale Fung, Anik Dey, Farhad Bin Siddique, Ruixi Lin, Yang Yang, Yan Wan and Ho Yin Ricky Chan

Kathaa: A Visual Programming Framework for NLP Applications Sharada Prasanna Mohanty, Nehal J Wani, Manish Srivastava and Dipti Misra Sharma

"Why Should I Trust You?": Explaining the Predictions of Any Classifier Marco Ribeiro, Sameer Singh and Carlos Guestrin

Included with your registration.

Enjoy a fun evening under the stars!

Bring your Flower Power to our SoCal Beach Party! After the main dinner and Poster Session, join us on the Bayview Lawn adjacent to the Pavilion for desserts, coffee, tea, and drinks (cash bar). A Beach Boys style band will entertain you when you are not busy in the VW Bus Photo Booth, talking amongst your friends and colleagues, or playing with the beach balls.

More...

Evaluating Natural Language Generation Systems

Natural Language Generation (NLG) systems have different characteristics than other NLP systems, which effects how they are evaluated. In particular, it can be difficult to meaningfully evaluate NLG texts by comparing them against gold-standard reference texts, because (A) there are usually many possible texts which are acceptable to users and (B) some NLG systems produce texts which are better (as judged by human users) than human-written corpus texts. Partially because of these reasons, the NLG community places much more emphasis on human-based evaluations than most areas of NLP.

I will discuss the various ways in which NLG systems are evaluated, focusing on human-based evaluations. These typically either measure the success of generated texts at achieving a goal (eg, measuring how many people change their behaviour after reading behaviour-change texts produced by an NLG system); or ask human subjects to rate various aspects of generated texts (such as readability, accuracy, and appropriateness), often on Likert scales. I will use examples from evaluations I have carried out, and highlight some of the lessons I have learnt, including the importance of reporting negative results, the difference between laboratory and real-world evaluations, and the need to look at worse-case as well as average-case performance. I hope my talk will be interesting and relevant to anyone who is interested in the evaluation of NLP systems.

Chair: Owen Rambow

Best Short Paper

Best Long Papers