Program

NAACL HLT 2018 Conference Handbook: Download

Overview

Saturday, June 2
Breakfast 07:30 - 08:45 Empire Foyer
Welcome from the Chairs 08:45 - 09:00 Empire Ballroom Chair: Marilyn Walker, Heng Ji and Amanda Stent
Keynote 1 (sponsored by Toutiao AI Lab): Why 72? 09:00 - 10:00 Empire Ballroom Chair: Marilyn Walker Speaker: Charles Yang
Morning Coffee 10:00 - 10:30 Empire Foyer
Information Extraction 1 10:30 - 11:30 Empire A	Phonology Morphology and Word Segmentation 1 10:30 - 11:30 Empire B	Speech 1 10:30 - 11:30 Empire C	Industry Track Machine Learning -- Classification 10:30 - 11:30 Empire D	Posters and Demos 10:30 - 12:00 Elite Hall B • Discourse and Pragmatics 1 • Generation 1 • NLP Applications 1 • Industry Track Generation • Industry Track NLP Applications
Machine Learning 1 11:30 - 12:30 Empire A	Information Extraction 2 11:30 - 12:30 Empire B	Machine Translation 1 11:30 - 12:30 Empire C	Industry Track Dialog 11:30 - 12:30 Empire D

Lunch 12:30 - 14:00
Industry Track Keynote: Building a Socialbot: Lessons Learned from 10M Conversations 14:00 - 15:00 Empire Ballroom Chair: Yunyao Li Speaker: Mari Ostendorf
Afternoon Coffee 15:00 - 15:30 Empire Foyer
Machine Learning 2 15:30 - 17:00 Empire A	Social Media and Computational Social Science 1 15:30 - 17:00 Empire B	Vision, Robotics and Other Grounding 1 15:30 - 17:00 Empire C	Industry Track Careers in the Industry Panel 15:30 - 17:00 Empire D Chair: Philip Resnik	Posters and Demos 15:30 - 17:00 Elite Hall B • Semantics 1 • Sentiment Analysis 1 • Industry Track Sentiment Analysis
NLP Applications 2 17:00 - 18:30 Empire A	Question Answering 1 17:00 - 18:30 Empire B	SRW highlight papers 17:00 - 18:30 Empire C	Industry Track Machine Translation 17:00 - 18:30 Empire D

Sunday, June 3
Breakfast 07:30 - 08:45 Empire Foyer
Announcements 08:45 - 09:00 Empire Ballroom
Keynote 2 (sponsored by Google): The Moment When the Future Fell Asleep 09:00 - 10:00 Empire Ballroom Chair: Amanda Stent Speaker: Kevin Knight
Morning Coffee 10:00 - 10:30 Empire Foyer
Cognitive Modeling and Psycholinguistics 1 10:30 - 11:30 Empire A	Summarization 1 10:30 - 11:30 Empire B	Semantics 2 10:30 - 11:30 Empire C	Industry Track Machine Learning -- Domain Adaptation 10:30 - 11:30 Empire D	Posters and Demos 10:30 - 12:00 Elite Hall B • Information Extraction 3 • Tagging Chunking Syntax and Parsing 1
Machine Learning 3 11:30 - 12:30 Empire A	Social Media and Computational Social Science 2 11:30 - 12:30 Empire B	Vision, Robotics and Other Grounding 2 11:30 - 12:30 Empire C	Industry Track Named Entity and Language Generation 11:30 - 12:30 Empire D

Lunch 12:30 - 14:00
Industry Track Keynote: Building innovative startups, products, and services – personal insights 14:00 - 15:00 Empire Ballroom Chair: Jennifer Chu-Carroll Speaker: Daniel Marcu				Posters and Demos 14:00 - 15:30 Elite Hall B • Phonology Morphology and Word Segmentation 2
Afternoon Coffee 15:00 - 15:30 Empire Foyer
Text Mining 1 15:30 - 17:00 Empire A	Semantics 3 15:30 - 17:00 Empire B	Tagging Chunking Syntax and Parsing 2 15:30 - 17:00 Empire C	Industry Track Ethics in NLP Panel 15:30 - 17:00 Empire D Chair: Dirk Hovy	Posters and Demos 15:30 - 17:00 Elite Hall B • Machine Learning 4 • Machine Translation 2 • Industry Track Machine Learning • Industry Track Machine Translation
Test of Time 17:15 - 18:30 Empire B

Monday, June 4
Breakfast 07:30 - 08:45 Empire Foyer
Announcements 08:45 - 09:00 Empire Ballroom
Keynote 3 (sponsored by Bloomberg): Google Assistant or My Assistant? Towards Personalized Situated Conversational Agents 09:00 - 10:00 Empire Ballroom Chair: Heng Ji Speaker: Dilek Hakkani-Tür
Morning Coffee 10:00 - 10:30 Empire Foyer
Information Extraction 3 10:30 - 11:30 Empire A	Semantics 3 10:30 - 11:30 Empire B	Generation 1 10:30 - 11:30 Empire C		Posters and Demos 10:30 - 12:00 Elite Hall B • Question Answering • Social Media and Computational Social Science • Summarization
Dialogue and Interactive Systems 11:30 - 12:30 Empire A	Information Extraction 4 11:30 - 12:30 Empire B	Generation 2 11:30 - 12:30 Empire C	Industry Track Machine Learning -- Prediction 11:30 - 12:30 Empire D

Lunch 12:30 - 14:00
Lunch 12:30 - 14:00			Business Meeting 13:00 - 14:00 Empire Ballroom
Sentiment Analysis 14:00 - 15:30 Empire A	Discourse 14:00 - 15:30 Empire B	Tagging Chunking Syntax and Parsing 2 14:00 - 15:30 Empire C	Posters and Demos 14:00 - 15:30 Elite Hall B • Cognitive Modeling and Psycholinguistics • Dialogue and Interactive Systems • Text Mining • Speech • Vision, Robotics and Other Grounding
Afternoon Coffee 15:30 - 16:00 Empire Foyer
Outstanding Papers and Closing Session 16:00 - 17:15 Empire Ballroom Chair: Joel Tetreault

Complete Program Schedule

Saturday, June 2
07:30 - 08:45	Breakfast - Empire Foyer
08:45 - 09:00	Welcome from the Chairs - Empire Ballroom Chair: Marilyn Walker, University of California Santa Cruz Heng Ji, Rensselaer Polytechnic Institute Amanda Stent, Bloomberg
09:00 - 10:00	Keynote 1 (sponsored by Toutiao AI Lab) - Empire Ballroom Chair: Marilyn Walker, University of California Santa Cruz
Why 72? Charles Yang, University of Pennsylvania
10:00 - 10:30	Morning Coffee - Empire Foyer
10:30 - 11:30	Session Oral: Information Extraction 1 - Empire A Chair: Dan Bikel, Google
10:30AM - 10:48AM Label-aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognition Zhenghui Wang¹, Yanru Qu¹, Liheng Chen¹, Jian Shen¹, Weinan Zhang¹, Shaodian Zhang², Yimei Gao³, Gen Gu³, Ken Chen³, Yong Yu¹ ¹Shanghai Jiao Tong University, ²Shanghai Jiao Tong University / Synyi LLC, ³Synyi LLC 10:48AM - 11:06AM Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss Peng Xu and Denilson Barbosa University of Alberta 11:06AM - 11:24 Joint Bootstrapping Machines for High Confidence Relation Extraction Pankaj Gupta¹, Benjamin Roth², Hinrich Schütze² ¹Ludwig Maximilian University of Munich / Siemens, ²Ludwig Maximilian University of Munich
10:30 - 11:30	Session Oral: Phonology Morphology and Word Segmentation 1 - Empire B Chair: Barbara Plank, University of Groningen
10:30AM - 10:48AM A Deep Generative Model of Vowel Formant Typology Ryan Cotterell and Jason Eisner Johns Hopkins University 10:48AM - 11:06AM Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages Katharina Kann¹, Jesus Manuel Mager Hois², Ivan Vladimir Meza Ruiz², Hinrich Schütze¹ ¹Ludwig Maximilian University of Munich, ²Universidad Nacional Autónoma de México 11:06AM - 11:24AM Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation Peyman Passban, Qun Liu, Andy Way ADAPT Centre
10:30 - 11:30	Session Oral: Speech 1 - Empire C Chair: Dilek Hakkani-Tur, Google Research
10:30AM - 10:48AM Parsing Speech: a Neural Approach to Integrating Lexical and Acoustic-Prosodic Information Trang Tran¹, Shubham Toshniwal², Mohit Bansal³, Kevin Gimpel², Karen Livescu², Mari Ostendorf¹ ¹University of Washington, ²Toyota Technological Institute at Chicago, ³University of North Carolina at Chapel Hill 10:48AM - 11:06AM Tied Multitask Learning for Neural Speech Translation Antonios Anastasopoulos and David Chiang University of Notre Dame 11:06AM - 11:24AM Please Clap: Modeling Applause in Campaign Speeches Jon Gillick and David Bamman University of California, Berkeley
10:30 - 11:30	[Industry Track] Session Oral: Machine Learning -- Classification - Empire D Chair: Luke Zettlemoyer, University of Washington
10:30AM - 10:47AM Scalable Wide and Deep Learning for Computer Assisted Coding Marilisa Amoia¹, Frank Diehl¹, Jesus Gimenez¹, Joel Pinto¹, Raphael Schumann², Fabian Stemmer¹, Paul Vozila¹, Yi Zhang¹ ¹Nuance Communications, ²Institute for Computational Linguistics, Heidelberg University 10:48AM - 11:05AM Neural Network based Extreme Classification and Similarity Models for Product Matching Kashif Shah¹, Selcuk Kopru¹, Jean David Ruvini² ¹eBay Research, ²eBay 11:06AM - 11:23AM A Scalable Neural Shortlisting-Reranking Approach for Large-Scale Domain Classification in Natural Language Understanding Young-Bum Kim, Dongchan Kim, Joo-Kyung Kim, Ruhi Sarikaya Amazon Alexa
10:30 - 12:00	Session Posters and Demos: Discourse and Pragmatics 1 - Elite Hall B Chair: Laura Perez, University of Edinburgh
Attentive Interaction Model: Modeling Changes in View in Argumentation Yohan Jo, Shivani Poddar, Byungsoo Jeon, Qinlan Shen, Carolyn Rose, Graham Neubig Carnegie Mellon University Automatic Focus Annotation: Bringing Formal Pragmatics Alive in Analyzing the Information Structure of Authentic Data Ramon Ziai and Detmar Meurers Universität Tübingen Dear Sir or Madam, May I Introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer Sudha Rao¹ and Joel Tetreault² ¹University Of Maryland, College Park, ²Grammarly Enhanced Word Representations for Bridging Anaphora Resolution Yufang Hou IBM Research Ireland Gender Bias in Coreference Resolution Rachel Rudinger, Jason Naradowsky, Brian Leonard, Benjamin Van Durme Johns Hopkins University Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods Jieyu Zhao¹, Tianlu Wang², Mark Yatskar³, Vicente Ordonez², Kai-Wei Chang¹ ¹University of California, Los Angeles, ²University of Virginia, ³Allen Institute for Artificial Intelligence Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraph Zeyu Dai and Ruihong Huang Texas A&M University Integrating Stance Detection and Fact Checking in a Unified Corpus Ramy Baly¹, Mitra Mohtarami¹, James Glass¹, Lluís Màrquez², Alessandro Moschitti², Preslav Nakov³ ¹Massachusetts Institute of Technology, ²Amazon, ³Qatar Computing Research Institute Is Something Better than Nothing? Automatically Predicting Stance-based Arguments Using Deep Learning and Small Labelled Dataset. Pavithra Rajendran¹, Danushka Bollegala¹, Simon Parsons² ¹University of Liverpool, ²Kings College London Multi-Task Learning for Argumentation Mining in Low-Resource Settings Claudia Schulz, Steffen Eger, Johannes Daxenberger, Tobias Kahse, Iryna Gurevych Technische Universität Darmstadt Neural Models for Reasoning over Multiple Mentions Using Coreference Bhuwan Dhingra¹, Qiao Jin², Zhilin Yang¹, William Cohen¹, Ruslan Salakhutdinov¹ ¹Carnegie Mellon University, ²University of Pittsburgh Alignment, Acceptance, and Rejection of Group Identities in Online Political Discourse (SRW) Hagyeong Shin and Gabriel Doyle
10:30 - 12:00	Session Posters and Demos: Generation 1 - Elite Hall B Chair: Laura Perez, University of Edinburgh
A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation Juraj Juraska, Panagiotis Karagiannis, Kevin Bowden, Marilyn Walker University of California, Santa Cruz A Melody-conditioned Lyrics Language Model Kento Watanabe¹, Yuichiroh Matsubayashi¹, Satoru Fukayama², Masataka Goto², Kentaro Inui³, Tomoyasu Nakano² ¹Tohoku University, ²National Institute of Advanced Industrial Science and Technology (AIST), ³Tohoku University / RIKEN AIP Automatic Dialogue Generation with Expressed Emotions Chenyang Huang, Osmar Zaiane, Amine Trabelsi, Nouha Dziri University of Alberta Discourse-Aware Neural Rewards for Coherent Text Generation Antoine Bosselut¹, Asli Celikyilmaz², Xiaodong He³, Jianfeng Gao², Po-Sen Huang², Yejin Choi⁴ ¹University of Washington, ²Microsoft Research, ³JD AI Research, ⁴University of Washington / Allen Institute for Artificial Intelligence Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network Chenliang Li, Weiran Xu, Si Li, Sheng Gao Beijing University of Posts and Telecommunications Natural Answer Generation with Heterogeneous Memory Yao Fu and Yansong Feng Peking University Natural Language Generation by Hierarchical Decoding with Linguistic Patterns Shang-Yu Su, Kai-Ling Lo, Yi Ting Yeh, Yun-Nung Chen National Taiwan University Neural Poetry Translation Marjan Ghazvininejad¹, Yejin Choi², Kevin Knight¹ ¹University of Southern California / Information Sciences Institute, ²University of Washington / Allen Institute for Artificial Intelligence Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation Shuming Ma¹, Xu Sun¹, Wei Li¹, Sujian Li¹, Wenjie Li², Xuancheng Ren¹ ¹Peking University, ²The Hong Kong Polytechnic University RankME: Reliable Human Ratings for Natural Language Generation Jekaterina Novikova, Ondřej Dušek, Verena Rieser Heriot-Watt University Sentence Simplification with Memory-Augmented Neural Networks Tu Vu¹, Baotian Hu², Tsendsuren Munkhdalai³, Hong Yu⁴ ¹University of Massachusetts, Amherst, ²University of Massachusetts Medical School, ³Microsoft Research, ⁴University of Massachusetts, Amherst / University of Massachusetts Medical School Simplification Using Paraphrases and Context-Based Lexical Substitution Reno Kriz¹, Eleni Miltsakaki², Marianna Apidianaki³, Chris Callison-Burch¹ ¹University of Pennsylvania, ²Choosito, Inc., ³University of Pennsylvania / LIMSI, CNRS Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types Hady Elsahar, Christophe Gravier, Frederique Laforest Université de Lyon
10:30 - 12:00	Session Posters and Demos: NLP Applications 1 - Elite Hall B Chair: Laura Perez, University of Edinburgh
A Corpus of Non-Native Written English Annotated for Metaphor Beata Beigman Klebanov, Chee Wee (Ben) Leong, Michael Flor Educational Testing Service A Simple and Effective Approach to the Story Cloze Test Siddarth Srinivasan, Richa Arora, Mark Riedl Georgia Institute of Technology An Annotated Corpus for Machine Reading of Instructions in Wet Lab Protocols Chaitanya Kulkarni, Wei Xu, Alan Ritter, Raghu Machiraju Ohio State University Annotation Artifacts in Natural Language Inference Data Suchin Gururangan¹, Swabha Swayamdipta², Omer Levy¹, Roy Schwartz³, Samuel Bowman⁴, Noah A. Smith¹ ¹University of Washington, ²Carnegie Mellon University, ³University of Washington / The Allen Institute for Artificial Intelligence, ⁴New York University Automated Essay Scoring in the Presence of Biased Ratings Evelin Amorim, Marcia Cançado, Adriano Veloso Universidade Federal de Minas Gerais Content-Based Citation Recommendation Chandra Bhagavatula¹, Sergey Feldman², Russell Power³, Waleed Ammar¹ ¹Allen Institute for Artificial Intelligence, ²Data Cowboys, ³- Humor Recognition Using Deep Learning Peng-Yu Chen and Von-Wun Soo National Tsing Hua University Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection Jing Qian, Mai ElSherief, Elizabeth Belding, William Yang Wang University of California, Santa Barbara Looking beyond the Surface:A Challenge Set for Reading Comprehension over Multiple Sentences Daniel Khashabi¹, Snigdha Chaturvedi², Michael Roth³, Shyam Upadhyay¹, Dan Roth¹ ¹University of Pennsylvania, ²University of California, Santa Cruz, ³Saarland University Neural Automated Essay Scoring and Coherence Modeling for Adversarially Crafted Input Youmna Farag, Helen Yannakoudakis, Ted Briscoe University of Cambridge QuickEdit: Editing Text & Translations by Crossing Words Out David Grangier and Michael Auli Facebook AI Research Reference-less Measure of Faithfulness for Grammatical Error Correction Leshem Choshen and Omri Abend The Hebrew University of Jerusalem Tempo-Lexical Context Driven Word Embedding for Cross-Session Search Task Extraction Procheta Sen¹, Debasis Ganguly², Gareth Jones¹ ¹ADAPT Centre, ²IBM Research, Dublin NLP Lean Programming Framework: Developing NLP Applications More Effectively (DEMO) Marc Schreiber, Bodo Kraft and Albert Zündorf Pay-Per-Request Deployment of Neural Network Models Using Serverless Architectures (DEMO) Zhucheng Tu, Mengping Li and Jimmy Lin An Automated Medical Scribe for Documenting Clinical Encounters (DEMO) Gregory Finley, Erik Edwards, Amanda Robinson, Najmeh Sadoughi, James Fone, Mark Miller, David Suendermann-Oeft, Michael Brenndoerfer and Nico Axtmann CL Scholar: The ACL Anthology Knowledge Graph Miner (DEMO) Mayank Singh, Pradeep Dogga, Sohan Patro, Dhiraj Barnwal, Ritam Dutt, Rajarshi Haldar, Pawan Goyal and Animesh Mukherjee
10:30 - 12:00	[Industry Track] Session Posters and Demos: Generation - Elite Hall B Chair: Laura Perez, University of Edinburgh
Quality Estimation for Automatically Generated Titles of eCommerce Browse Pages Nicola Ueffing¹, José G. C. de Souza², Gregor Leusch¹ ¹eBay, ²eBay Inc.
10:30 - 12:00	[Industry Track] Session Posters and Demos: NLP Applications - Elite Hall B Chair: Laura Perez, University of Edinburgh
Atypical Inputs in Educational Applications Su-Youn Yoon¹, Aoife Cahill¹, Anastassia Loukina¹, Klaus Zechner², Brian Riordan², Nitin Madnani¹ ¹Educational Testing Service, ²ETS Using Aspect Extraction Approaches to Generate Review Summaries and User Profiles Christopher Mitcheltree, Veronica Wharton, Avneesh Saluja Airbnb SystemT: Declarative Text Understanding for Enterprise Laura Chiticariu¹, Marina Danilevsky², Yunyao Li¹, Frederick Reiss³, Huaiyu Zhu¹ ¹IBM Research - Almaden, ²IBM Research, ³IBM Construction of the Literature Graph in Semantic Scholar Waleed Ammar¹, Dirk Groeneveld¹, Chandra Bhagavatula¹, Iz Beltagy¹, Miles Crawford¹, Doug Downey², Jason Dunkelberger¹, Ahmed Elgohary³, Sergey Feldman⁴, Vu Ha¹, Rodney Kinney¹, Sebastian Kohlmeier⁵, Kyle Lo¹, Tyler Murray¹, Hsu-Han Ooi¹, Matthew Peters¹, Joanna Power¹, Sam Skjonsberg¹, Lucy Wang⁶, Chris Willhelm¹, Zheng Yuan², Madeleine van Zuylen¹, oren etzioni⁷ ¹Allen Institute for Artificial Intelligence, ²Northwestern University, ³University of Maryland, College Park, ⁴Data Cowboys, ⁵Allen Institute for Artificial Intelligence (AI2), ⁶University of Washington, ⁷AI2
11:30 - 12:30	Session Oral: Machine Learning 1 - Empire A Chair: Raymond Mooney, The University of Texas at Austin
11:30AM - 11:48AM Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens Marek Rei¹ and Anders Søgaard² ¹University of Cambridge, ²University of Copenhagen 11:48AM - 12:06PM Variable Typing: Assigning Meaning to Variables in Mathematical Text Yiannos Stathopoulos, Simon Baker, Marek Rei, Simone Teufel University of Cambridge 12:06 PM - 12:23 PM Learning Structured Text Representations (TACL) Yang Liu and Mirella Lapata
11:30 - 12:30	Session Oral: Information Extraction 2 - Empire B Chair: Mihai Surdeanu, University of Arizona
11:30AM - 11:48AM Learning beyond Datasets: Knowledge Graph Augmented Neural Networks for Natural Language Processing Annervaz K M¹, Somnath Basu Roy Chowdhury², Ambedkar Dukkipati³ ¹Indian Institute of Science / Accenture Technology Labs, ²Indian Institute of Technology, Kharagpur, ³Indian Institute of Science 11:48AM - 12:06PM Comparing Constraints for Taxonomic Organization Anne Cocos¹, Marianna Apidianaki², Chris Callison-Burch¹ ¹University of Pennsylvania, ²University of Pennsylvania / LIMSI, CNRS 12:06PM - 12:24PM Cross-Lingual Syntactic Transfer with Limited Resources (TACL) Mohammad Sadegh Rasooli and Michael Collins
11:30 - 12:30	Session Oral: Machine Translation 1 - Empire C Chair: Daniel Marcu, Amazon
11:30AM - 11:48AM Improving Lexical Choice in Neural Machine Translation Toan Nguyen and David Chiang University of Notre Dame 11:48AM - 12:06PM Universal Neural Machine Translation for Extremely Low Resource Languages Jiatao Gu¹, Hany Hassan², Jacob Devlin³, Victor O.K. Li¹ ¹The University of Hong Kong, ²Microsoft Research, ³Google Research 12:06PM - 12:24PM Classical Structured Prediction Losses for Sequence to Sequence Learning Sergey Edunov, Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato Facebook AI Research
11:30 - 12:30	[Industry Track] Session Oral: Dialog - Empire D Chair: Owen Rambow, Elemental Cognition, LLC
11:30AM - 11:47AM What we need to learn if we want to do and not just talk Rashmi Gangadharaiah, Balakrishnan Narayanaswamy, Charles Elkan Amazon 11:48AM - 12:05PM Data Collection for Dialogue System: A Startup Perspective Yiping Kang¹, Yunqi Zhang¹, Jonathan K. Kummerfeld², Lingjia Tang¹, Jason Mars¹ ¹University of Michigan, Clinc, Inc., ²University of Michigan 12:06PM - 12:23PM Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning Pararth Shah¹, Dilek Hakkani-Tur¹, Bing Liu², Gokhan Tur¹ ¹Google Inc, ²Carnegie Mellon University
12:30 - 14:00	Lunch
14:00 - 15:00	Industry Track Keynote 1 - Empire Ballroom Chair: Yunyao Li, IBM Research - Almaden
Building a Socialbot: Lessons Learned from 10M Conversations Mari Ostendorf, University of Washington
15:00 - 15:30	Afternoon Coffee - Empire Foyer
15:30 - 17:00	Session Oral: Machine Learning 2 - Empire A Chair: Hal Daumé III, University of Maryland
3:30PM - 3:47PM Deep Dirichlet Multinomial Regression Adrian Benton and Mark Dredze Johns Hopkins University 3:48PM - 4:06PM Training Structured Prediction Energy Networks with Indirect Supervision Amirmohammad Rooshenas, Aishwarya Kamath, Andrew McCallum University of Massachusetts, Amherst 4:06PM - 4:23PM Anchored Correlation Explanation: Topic Modeling With Minimal Domain Knowledge (TACL) Ryan J. Gallagher, Kyle Reing, David Kale, Greg Ver Steeg 4:24 PM - 4:42 PM Aspect-augmented Adversarial Networks for Domain Adaptation (TACL) Yuan Zhang, Regina Barzilay, Tommi Jaakkola
15:30 - 17:00	Session Oral: Social Media and Computational Social Science 1 - Empire B Chair: Margaret Mitchell, Google
3:30PM - 3:48PM Microblog Conversation Recommendation via Joint Modeling of Topics and Discourse Xingshan Zeng¹, Jing Li², Lu Wang³, Nicholas Beauchamp³, Sarah Shugars³, Kam-Fai Wong¹ ¹The Chinese University of Hong Kong / 3MoE Key Laboratory of High Confidence Software Technologies, ²Tencent AI Lab, ³Northeastern University 3:48PM - 4:06PM Before Name-calling: Dynamics and Triggers of Ad Hominem Fallacies in Web Argumentation Ivan Habernal¹, Henning Wachsmuth², Iryna Gurevych¹, Benno Stein² ¹Technische Universität Darmstadt, ²Bauhaus-Universität Weimar 4:06PM - 4:24PM Si O No, Que Penses? Catalonian Independence and Linguistic Identity on Social Media Ian Stewart, Yuval Pinter, Jacob Eisenstein Georgia Institute of Technology 4:24PM - 4:42PM Multiple Instance Learning Networks for Fine-Grained Sentiment Analysis (TACL) Stefanos Angelidis and Mirella Lapata
15:30 - 17:00	Session Oral: Vision, Robotics and Other Grounding 1 - Empire C Chair: Mirella Lapata, University of Edinburgh
3:30PM - 3:47PM Scene Graph Parsing as Dependency Parsing Yu-Siang Wang¹, Chenxi Liu², Xiaohui Zeng³, Alan Yuille² ¹National Taiwan University, ²Johns Hopkins University, ³Hong Kong University of Science and Technology 3:48PM - 4:05PM Learning Visually Grounded Sentence Representations Douwe Kiela¹, Alexis Conneau¹, Allan Jabri², Maximilian Nickel¹ ¹Facebook AI Research, ²University of California, Berkeley 4:06PM - 4:23PM Comparatives, Quantifiers, Proportions: a Multi-Task Model for the Learning of Quantities from Vision Sandro Pezzelle¹, Ionut-Teodor Sorodoc², Raffaella Bernardi¹ ¹University of Trento, ²University of Trento / Universitat Pompeu Fabra Barcelona 4:24PM - 4:42PM Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets Wei-Lun Chao, Hexiang Hu, Fei Sha University of Southern California
15:30 - 17:00	Careers in the Industry Panel - Empire D Chair: Philip Resnik, University of Maryland, College Park
15:30 - 17:00	Session Posters and Demos: Semantics 1 - Elite Hall B Chair: Scott Wen-tau Yih, Allen Institute for Artificial Intelligence
A Transition-based Algorithm for Unrestricted AMR Parsing David Vilares and Carlos Gómez-Rodríguez Universidade da Coruña Abstract Meaning Representation for Paraphrase Detection Fuad Issa¹, Marco Damonte¹, Shay B. Cohen¹, Xiaohui Yan², Yi Chang² ¹University of Edinburgh, ²Huawei Analogies in Complex Verb Meaning Shifts: the Effect of Affect in Semantic Similarity Models Maximilian Köper and Sabine Schulte im Walde Universität Stuttgart Attr2Vec: Jointly Learning Word and Contextual Attribute Embeddings with Factorization Machines Fabio Petroni¹, Vassilis Plachouras², Timothy Nugent¹, Jochen L. Leidner¹ ¹Thomson Reuters, ²Facebook Can Network Embedding of Distributional Thesaurus Be Combined with Word Vectors for Better Representation? Abhik Jana and Pawan Goyal Indian Institute of Technology, Kharagpur Character-based Neural Networks for Sentence Pair Modeling Wuwei Lan and Wei Xu Ohio State University Deep Neural Models of Semantic Shift Alex Rosenfeld and Katrin Erk The University of Texas at Austin Determining Event Durations: Models and Error Analysis Alakananda Vempala, Eduardo Blanco, Alexis Palmer University Of North Texas Diachronic Usage Relatedness (DURel):  A Framework for the Annotation of Lexical Semantic Change Dominik Schlechtweg¹, Sabine Schulte im Walde¹, Stefanie Eckmann² ¹Universität Stuttgart, ²Ludwig Maximilian University of Munich Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings Yan Song, Shuming Shi, Jing Li, Haisong Zhang Tencent AI Lab Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model Goran Glavaš¹ and Ivan Vulić² ¹University of Mannheim, ²University of Cambridge Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection Haw-Shiuan Chang¹, Ziyun Wang², Luke Vilnis¹, Andrew McCallum¹ ¹University of Massachusetts, Amherst, ²Tsinghua University Evaluating bilingual word embeddings on the long tail Fabienne Braune¹, Viktor Hangya², Tobias Eder², Alexander Fraser² ¹Ludwig Maximilian University of Munich / Volkswagen Data Lab Munich, ²Ludwig Maximilian University of Munich Frustratingly Easy Meta-Embedding -- Computing Meta-Embeddings by Averaging Source Word Embeddings Joshua Coates and Danushka Bollegala University of Liverpool Introducing Two Vietnamese Datasets for Evaluating Semantic Models of (Dis-)Similarity and Relatedness Kim Anh Nguyen, Sabine Schulte im Walde, Ngoc Thang Vu Universität Stuttgart Lexical Substitution for Evaluating Compositional Distributional Models Maja Buljan¹, Sebastian Padó¹, Jan Šnajder² ¹Universität Stuttgart, ²University of Zagreb Mining Possessions: Existence, Type and Temporal Anchors Dhivya Chinnappa and Eduardo Blanco University of North Texas Mittens: an Extension of GloVe for Learning Domain-Specialized Representations Nicholas Dingwall¹ and Christopher Potts² ¹Roam Analytics, ²Stanford University Neural Tensor Networks with Diagonal Slice Matrices Takahiro Ishihara¹, Katsuhiko Hayashi², Hitoshi Manabe¹, Masashi Shimbo¹, Masaaki Nagata³ ¹Nara Institute of Science and Technology, ²Osaka University, ³NTT Communication Science Laboratories Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds Using Paraphrases in a Neural Model Vered Shwartz¹ and Chris Waterson² ¹Bar-Ilan University, ²Google Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources Ivan Vulić¹, Goran Glavaš², Nikola Mrkšić³, Anna Korhonen¹ ¹University of Cambridge, ²University of Mannheim, ³PolyAI Semantic Pleonasm Detection Omid Kashefi, Andrew T. Lucas, Rebecca Hwa University of Pittsburgh Similarity Measures for the Detection of Clinical Conditions with Verbal Fluency Tasks FFelipe Paula¹, Rodrigo Wilkens², Marco Idiart¹, Aline Villavicencio³ ¹Universidade Federal do Rio Grande do Sul, ²Université Catholique de Louvain, ³Universidade Federal do Rio Grande do Sul / University of Essex Sluice Resolution without Hand-crafted Features over Brittle Syntax Trees Ola Rønning¹, Daniel Hardt², Anders Søgaard¹ ¹University of Copenhagen, ²Copenhagen Business School The Word Analogy Testing Caveat Natalie Schluter IT University of Copenhagen Transition-based Chinese AMR Parsing Chuan Wang¹, Bin Li², Nianwen Xue¹ ¹Brandeis University, ²Nanjing Normal University Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features Matteo Pagliardini¹, Prakhar Gupta², Martin Jaggi² ¹Iprova SA, ²École Polytechnique Fédérale de Lausanne Towards qualitative word embeddings evaluation: measuring neighbors variation (SRW) Benedicte Pierrejean and Ludovic Tanguy A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge (SRW) Ali Emami, Adam Trischler, Kaheer Suleman and Jackie Chi Kit Cheung Argumentext: Searching Arguments in Heterogeneous Sources (DEMO) Christian Stab, Johannes Daxenberger, Chris Stahlhut, Tristan Miller, Benjamin Schiller, Christopher Tauchmann, Steffen Eger and Iryna Gurevych ClaimRank: Detecting Check-Worthy Claims in Arabic and English (DEMO) Israa Jaradat, Pepa Gencheva, Alberto Barrón-Cedeño, Lluís Màrquez and Preslav Nakov Combining Abstractness and Language-specific Theoretical Indicators for Detecting Non-Literal Usage of Estonian Particle Verbs (SRW) Eleri Aedmaa, Maximilian Köper and Sabine Schulte im Walde A Deeper Look into Dependency-Based Word Embeddings (SRW) Sean MacAvaney and Amir Zeldes Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings (TACL) Hanan Aldarmaki, Mahesh Mohan and Mona Diab Verb Alternations and Their Impact on Frame Induction (SRW) Esther Seyffarth
15:30 - 17:00	Session Posters and Demos: Sentiment Analysis 1 - Elite Hall B Chair: Scott Wen-tau Yih, Allen Institute for Artificial Intelligence
Knowledge-enriched Two-layered Attention Network for Sentiment Analysis Abhishek Kumar¹, Daisuke Kawahara², Sadao Kurohashi² ¹Indian Institute of Technology, Patna, ²Kyoto University Learning Domain Representation for Multi-Domain Sentiment Classification Qi Liu¹, Yue Zhang¹, Jiangming Liu² ¹Singapore University of Technology and Design, ²University of Edinburgh Learning Sentence Representations over Tree Structures for Target-dependent Classification Junwen Duan, Xiao Ding, Ting Liu Harbin Institute of Technology Letting Emotions Flow: Success Prediction by Modeling the Flow of Emotions in Books Suraj Maharjan¹, Sudipta Kar¹, Manuel Montes², Fabio A. Gonzalez³, Thamar Solorio¹ ¹University of Houston, ²Instituto Nacional de Astrofísica, Óptica y Electrónica, ³Universidad Nacional de Colombia Modeling Inter-Aspect Dependencies for Aspect-Based Sentiment Analysis Devamanyu Hazarika¹, Soujanya Poria², Prateek Vij³, Gangeshwar Krishnamurthy², Erik Cambria⁴, Roger Zimmermann¹ ¹National University of Singapore, ²ASTAR, ³Indian Institute of Technology, Guwahati, ⁴Nanyang Technological University Multi-task Learning Framework for Mining Crowd Intelligence towards Clinical Treatment* Shweta Yadav¹, Asif Ekbal¹, Sriparna Saha¹, Pushpak Bhattacharyya¹, Amit Sheth² ¹Indian Institute of Technology, Patna, ²Wright State University Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis Fei Liu, Trevor Cohn, Timothy Baldwin The University of Melbourne Relevant Emotion Ranking from Text Constrained with Emotion Relationships Deyu Zhou¹, Yang Yang¹, Yulan He² ¹Southeast University, ²Aston University Solving Data Sparsity for Aspect Based Sentiment Analysis Using Cross-linguality and Multi-linguality Md Shad Akhtar¹, Palaash Sawant², Sukanta Sen¹, Asif Ekbal¹, Pushpak Bhattacharyya¹ ¹Indian Institute of Technology, Patna, ²Goa University SRL4ORL: Improving Opinion Role Labeling Using Multi-Task Learning with Semantic Role Labeling Ana Marasović and Anette Frank Heidelberg University 360° Stance Detection (DEMO) Sebastian Ruder, John Glover, Afshin Mehrabani and Parsa Ghaffari DebugSL: An Interactive Tool for Debugging Sentiment Lexicons (DEMO) Andrew Schneider, John Male, Saroja Bhogadhi and Eduard Dragut Learning Word Embeddings for Data Sparse and Sentiment Rich Data Sets (SRW) Prathusha Kameswara Sarma
15:30 - 17:00	[Industry Track] Session Posters and Demos: Sentiment Analysis - Empire D Chair: Scott Wen-tau Yih, Allen Institute for Artificial Intelligence
Benchmarks and models for entity-oriented polarity detection Lidia Pivovarova, Arto Klami, Roman Yangarber University of Helsinki
17:00 - 18:30	Session Oral: NLP Applications 2 - Empire A Chair: Yang Liu, University of Texas at Dallas
5:00PM - 5:18PM Approaching Neural Grammatical Error Correction as a Low-Resource Machine Translation Task Marcin Junczys-Dowmunt¹, Roman Grundkiewicz², Shubha Guha², Kenneth Heafield² ¹Microsoft, ²University of Edinburgh 5:18PM - 5:36PM Robust Cross-lingual Hypernymy Detection Using Dependency Context Shyam Upadhyay¹, Yogarshi Vyas², Marine Carpuat², Dan Roth¹ ¹University of Pennsylvania, ²University of Maryland, College Park 5:36PM - 5:54PM Noising and Denoising Natural Language: Diverse Backtranslation for Grammar Correction Ziang Xie, Guillaume Genthial, Stanley Xie, Andrew Ng, Dan Jurafsky Stanford University 5:54PM - 6:12PM Towards Evaluating Narrative Quality In Student Writing (TACL) Swapna Somasundaran, Michael Flor, Martin Chodorow, Hillary Molloy, Binod Gyawali and Laura McCulla 6:12PM - 6:30PM Near Human-Level Performance in Grammatical Error Correction with Hybrid Machine Translation Roman Grundkiewicz¹ and Marcin Junczys-Dowmunt² ¹University of Edinburgh, ²Microsoft
17:00 - 18:30	Session Oral: Question Answering 1 - Empire B Chair: Avirup Sil, IBM
5:00PM - 5:18PM Self-Training for Jointly Learning to Ask and Answer Questions Mrinmaya Sachan and Eric Xing Carnegie Mellon University 5:18PM - 5:36PM The Web as a Knowledge-base for Answering Complex Questions Alon Talmor and Jonathan Berant Tel Aviv University 5:36PM - 5:54PM A Meaning-based Statistical English Math Word Problem Solver Chao-Chun Liang, Yu-Shiang Wong, Yi-Chung Lin, Keh-Yih Su Academia Sinica 5:54PM - 6:12PM Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networks Salman Mohammed, Peng Shi, Jimmy Lin University of Waterloo 6:12 PM - 6:30 PM Questionable Answers in Question Answering Research: Reproducibility and Variability of Published Results (TACL) Matt Crane
17:00 - 18:30	Session Oral: SRW highlight papers - Empire C Chair: Shereen Oraby, University of California, Santa Cruz Umashanthi Pavalanathan, Georgia Institute of Technology Kyeongmin Rim, Brandeis University
5:00 PM - 5:14 PM Igbo Diacritic Restoration using Embedding Models Ignatius Ezeani, Mark Hepple, Ikechukwu Onyenwe and Enemouh Chioma 5:15 PM - 5:29 PM Using Classifier Features to Determine Language Transfer on Morphemes Alexandra Lavrentovich 5:30 PM - 5:44 PM End-to-End Learning of Task-Oriented Dialogs Bing Liu and Ian Lane 5:45 PM - 5:59 PM Towards generating personalized hospitalization summaries Sabita Acharya, Barbara Di Eugenio, Andrew Boyd, Richard Cameron, Karen Dunn Lopez, Pamela Martyn-Nemeth, Carolyn Dickens and Amer Ardati 6:00 PM - 6:14 PM A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge Ali Emami, Adam Trischler, Kaheer Suleman and Jackie Chi Kit Cheung 6:15 PM - 6:30 PM Alignment, Acceptance, and Rejection of Group Identities in Online Political Discourse Hagyeong Shin and Gabriel Doyle
17:00 - 18:30	[Industry Track] Session Oral: Machine Translation - Empire D Chair: Kenneth Heafield, University of Edinburgh
5:00PM - 5:17PM Can Neural Machine Translation be Improved with User Feedback? Julia Kreutzer¹, Shahram Khadivi², Evgeny Matusov², Stefan Riezler³ ¹Department of Computational Linguistics, Heidelberg University, ²eBay, ³Heidelberg University 5:18PM - 5:35PM Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment Gonzalo Iglesias¹, William Tambellini¹, Adrià de Gispert², Eva Hasler², Bill Byrne³ ¹SDL, ²SDL Research, ³University of Cambridge 5:36PM - 5:53PM Pieces of Eight: 8-bit Neural Machine Translation Jerry Quinn and Miguel Ballesteros IBM Research 5:54PM - 6:12PM From dictations to clinical reports using machine translation Gregory Finley¹, Wael Salloum², Najmeh Sadoughi¹, Erik Edwards¹, Amanda Robinson¹, Nico Axtmann³, Michael Brenndoerfer⁴, Mark Miller¹, David Suendermann-Oeft⁵ ¹EMR.AI, ²Columbia University, ³DHBW, ⁴University of California, EMR.AI, ⁵ETS

Sunday, June 3
07:30 - 08:45	Breakfast - Empire Foyer
08:45 - 09:00	Announcements - Empire Ballroom Chair: Marilyn Walker, University of California, Santa Cruz
09:00 - 10:00	Keynote 2 (sponsored by Google) - Empire Ballroom Chair: Amanda Stent, Bloomberg
The Moment When the Future Fell Asleep Kevin Knight, University of Southern California / Information Sciences Institute
10:00 - 10:30	Morning Coffee - Empire Foyer
10:30 - 11:30	Session Oral: Cognitive Modeling and Psycholinguistics 1 - Empire A Chair: Kristy Hollingshead Seitz, Institute for Human & Machine Cognition
10:30AM - 10:48AM Fine-grained Temporal Orientation and its Relationship with Psycho-demographic Correlates Sabyasachi Kamila¹, Mohammed Hasanuzzaman², Asif Ekbal¹, Pushpak Bhattacharyya¹, Andy Way² ¹Indian Institute of Technology, Patna, ²ADAPT Centre 10:48AM - 11:06AM Querying Word Embeddings for Similarity and Relatedness Fatemeh Torabi Asr¹, Robert Zinkov², Michael Jones³ ¹Simon Fraser University, ²University of Oxford, ³Indiana University 11:06AM - 11:24AM Looking for Structure in Lexical and Acoustic-prosodic Entrainment Behaviors Andreas Weise¹ and Rivka Levitan² ¹The Graduate Center, CUNY, ²Brooklyn College, CUNY
10:30 - 11:30	Session Oral: Summarization 1 - Empire B Chair: Rada Mihalcea, University of Michigan
10:30AM - 10:48AM Semantic Structural Evaluation for Text Simplification Elior Sulem, Omri Abend, Ari Rappoport The Hebrew University of Jerusalem 10:48AM - 11:06AM Entity Commonsense Representation for Neural Abstractive Summarization Reinald Kim Amplayo, Seonjae Lim, Seung-won Hwang Yonsei University 11:06AM - 11:24AM Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies Max Grusky, Mor Naaman, Yoav Artzi Cornell Tech
10:30 - 11:30	Session Oral: Semantics 2 - Empire C Chair: Jonathan May, University of Southern California / Information Sciences Institute
10:30AM - 10:48AM Polyglot Semantic Parsing in APIs Kyle Richardson¹, Jonathan Berant², Jonas Kuhn¹ ¹Universität Stuttgart, ²Tel Aviv University 10:48AM - 11:06AM Modeling Semantic Plausibility by Injecting World Knowledge Su Wang, Greg Durrett, Katrin Erk The University of Texas at Austin 11:06AM - 11:24AM Neural Models of Factuality Rachel Rudinger¹, Aaron Steven White², Benjamin Van Durme¹ ¹Johns Hopkins University, ²University of Rochester
10:30 - 11:30	[Industry Track] Session Oral: Machine Learning -- Domain Adaptation - Empire D Chair: Mohit Bansal, University of North Carolina at Chapel Hill
10:30AM - 10:47AM Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System Judith Gaspers¹, Penny Karanasou¹, Rajen Chatterjee² ¹Amazon, ²University of Trento Trento 10:48AM - 11:05AM Fast and Scalable Expansion of Natural Language Understanding Functionality for Intelligent Agents Anuj Kumar Goyal, Angeliki Metallinou, Spyros Matsoukas Amazon 11:05AM - 11:22AM Bag of Experts Architectures for Model Reuse in Conversational Language Understanding Rahul Jha¹, Alex Marin¹, Suvamsh Shivaprasad¹, Imed Zitouni² ¹Microsoft Corporation, ²Microsoft
10:30 - 12:00	Session Posters and Demos: Information Extraction 3 - Elite Hall B Chair: Marine Carpuat, University of Maryland College Park
A Bi-model Based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling Yu Wang, Yilin Shen, Hongxia Jin Samsung Research America A Comparison of Two Paraphrase Models for Taxonomy Augmentation Vassilis Plachouras¹, Fabio Petroni², Timothy Nugent², Jochen L. Leidner² ¹Facebook, ²Thomson Reuters A Laypeople Study on Terminology Identification across Domains and Task Definitions Anna Hätty¹ and Sabine Schulte im Walde² ¹Robert Bosch GmbH, ²University of Stuttgart A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network Dai Quoc Nguyen¹, Tu Dinh Nguyen¹, Dat Quoc Nguyen², Dinh Phung¹ ¹Deakin University, ²The University of Melbourne Accurate Text-Enhanced Knowledge Graph Representation Learning Bo An, Bo Chen, Xianpei Han, Le Sun Chinese Academy of Sciences Acquisition of Phrase Correspondences Using Natural Deduction Proofs Hitomi Yanaka¹, Koji Mineshima², Pascual Martínez-Gómez³, Daisuke Bekki² ¹The University of Tokyo, ²Ochanomizu University, ³Artificial Intelligence Research Center, AIST Automatic Stance Detection Using End-to-End Memory Networks Mitra Mohtarami¹, Ramy Baly¹, James Glass¹, Preslav Nakov², Lluís Màrquez³, Alessandro Moschitti³ ¹Massachusetts Institute of Technology, ²Qatar Computing Research Institute, ³Amazon Collective Entity Disambiguation with Structured Gradient Tree Boosting Yi Yang, Ozan Irsoy, Kazi Shefaet Rahman Bloomberg LP Cross-language Article Linking Using Cross-Encyclopedia Entity Embedding Chun-Kai Wu¹ and Richard Tzong-Han Tsai² ¹National Tsing Hua University., ²National Central University DeepAlignment: Unsupervised Ontology Matching with Refined Word Vectors Prodromos Kolyvakis¹, Alexandros Kalousis², Dimitris Kiritsis¹ ¹École Polytechnique Fédérale de Lausanne, ²University of Applied Sciences Efficient Sequence Learning with Group Recurrent Networks Fei Gao¹, Lijun Wu², Li Zhao³, Tao Qin³, Xueqi Cheng⁴, Tie-Yan Liu³ ¹Chinese Academy of Sciences / Microsoft Research, ²Sun Yat-sen University, ³Microsoft Research, ⁴Chinese Academy of Sciences FEVER: a Large-scale Dataset for Fact Extraction and VERification James Thorne¹, Andreas Vlachos¹, Christos Christodoulopoulos², Arpit Mittal² ¹University of Sheffield, ²Amazon Global Relation Embedding for Relation Extraction Yu Su¹, Honglei Liu¹, Semih Yavuz¹, Izzeddin Gur¹, Huan Sun², Xifeng Yan¹ ¹University of California, Santa Barbara, ²The Ohio State University Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations Prafulla Kumar Choubey, Kaushik Raju, Ruihong Huang Texas A&M University Implicit Argument Prediction with Event Knowledge Pengxiang Cheng and Katrin Erk The University of Texas at Austin Improve Neural Entity Recognition via Multi-Task Data Selection and Constrained Decoding Huasha Zhao¹, Yi Yang², Qiong Zhang¹, Luo Si¹ ¹Alibaba Group, ²Alibaba Group / Nanjing University Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource Qiang Ning¹, Hao Wu², Haoruo Peng¹, Dan Roth² ¹University of Illinois at Urbana Champaign, ²University of Pennsylvania Keep Your Bearings: Lightly-supervised Information Extraction with Ladder Networks That Avoids Semantic Drift Ajay Nagesh and Mihai Surdeanu University of Arizona Multimodal Named Entity Recognition for Short Social Media Posts Seungwhan Moon¹, Leonardo Neves², Vitor Carvalho³ ¹Carnegie Mellon University / Snap Research, ²Snap Research, ³Intuit Nested Named Entity Recognition Revisited Arzoo Katiyar and Claire Cardie Cornell University Semi-Supervised Event Extraction with Paraphrase Clusters James Ferguson, Colin Lockard, Daniel Weld, Hannaneh Hajishirzi University of Washington Simultaneously Self-attending to All Mentions for Full-Abstract Biological Relation Extraction Patrick Verga, Emma Strubell, Andrew McCallum University of Massachusetts, Amherst Structure Regularized Neural Network for Entity Relation Classification for Chinese Literature Text Ji Wen, Xu Sun, Xuancheng Ren, Qi Su Peking University Supervised Open Information Extraction Gabriel Stanovsky¹, Julian Michael², Luke Zettlemoyer², Ido Dagan³ ¹University of Washington / Allen Institute for Artificial Intelligence, ²University of Washington, ³Bar-Ilan University Syntactic Patterns Improve Information Extraction for Medical Search Roma Patel¹, Yinfei Yang², Iain Marshall³, Ani Nenkova¹, Byron Wallace⁴ ¹University of Pennsylvania, ²Google, ³King's College London, ⁴Northeastern Syntactically Aware Neural Architectures for Definition Extraction Luis Espinosa Anke and Steven Schockaert Cardiff University CliCR: a Dataset of Clinical Case Reports for Machine Reading Comprehension Simon Suster¹ and Walter Daelemans² ¹University of Antwerp, ²University of Antwerp, CLiPS ELISA-EDL: A Cross-Lingual Entity Extraction, Linking and Localization System (DEMO) Boliang Zhang, Ying Lin, Xiaoman Pan, Di Lu, Jonathan May, Kevin Knight and Heng Ji Entity Resolution and Location Disambiguation in Ancient Hindu Temples Domain Using Web Data (DEMO) Ayush Maheshwari, Vishwajeet Kumar, Ganesh Ramakrishnan and J. Saketha Nath Read and Comprehend by Gated-Attention Reader with More Belief (SRW) Haohui Deng and Yik-Cheung Tam Cross-language Article Linking using Cross-Encyclopedia Entity Embedding (SRW) Chun-Kai Wu and Richard Tzong-Han Tsai
10:30 - 12:00	Session Posters and Demos: Tagging Chunking Syntax and Parsing 1 - Elite Hall B Chair: Marine Carpuat, University of Maryland College Park
A Dynamic Oracle for Linear-Time 2-Planar Dependency Parsing Daniel Fernández-González and Carlos Gómez-Rodríguez Universidade da Coruña Are Automatic Methods for Cognate Detection Good Enough for Phylogenetic Reconstruction in Historical Linguistics? Taraka Rama¹, Johann-Mattis List², Johannes Wahle³, Gerhard Jäger³ ¹University of Oslo, ²Max Planck Institute for the Science of Human History, ³University Tübingen Automatically Selecting the Best Dependency Annotation Design with Dynamic Oracles Guillaume Wisniewski¹, Ophélie Lacroix², François Yvon¹ ¹LIMSI, CNRS, ²Siteimprove Consistent CCG Parsing over Multiple Sentences for Improved Logical Reasoning Masashi Yoshikawa¹, Koji Mineshima², Hiroshi Noji³, Daisuke Bekki² ¹Nara Institute of Science and Technology, ²Ochanomizu University, ³Artificial Intelligence Research Center, AIST Embedding Syntax and Semantics of Prepositions via Tensor Decomposition Hongyu Gong, Suma Bhat, Pramod Viswanath University of Illinois at Urbana Champaign Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-projective Trees Lauriane Aufrant¹, Guillaume Wisniewski², François Yvon² ¹LIMSI, CNRS / DGA, ²LIMSI, CNRS From Phonology to Syntax: Unsupervised Linguistic Typology at Different Levels with Language Embeddings Johannes Bjerva and Isabelle Augenstein University of Copenhagen Improving Coverage and Runtime Complexity for Exact Inference in Non-Projective Transition-Based Dependency Parsers Tianze Shi¹, Carlos Gómez-Rodríguez², Lillian Lee¹ ¹Cornell University, ²Universidade da Coruña Monte Carlo Syntax Marginals for Exploring and Using Dependency Parses Katherine Keith, Su Lin Blodgett, Brendan O'Connor University of Massachusetts, Amherst Neural Particle Smoothing for Sampling from Conditional Sequence Models Chu-Cheng Lin and Jason Eisner Johns Hopkins University Neural Syntactic Generative Models with Exact Marginalization Jan Buys¹ and Phil Blunsom² ¹University of Oxford / University of Washington, ²University of Oxford / DeepMind Noise-Robust Morphological Disambiguation for Dialectal Arabic Nasser Zalmout, Alexander Erdmann, Nizar Habash New York University, Abu Dhabi Parsing Tweets into Universal Dependencies Yijia Liu¹, Yi Zhu², Wanxiang Che¹, Bing Qin¹, Nathan Schneider³, Noah A. Smith⁴ ¹Harbin Institute of Technology, ²University of Cambridge, ³Georgetown University, ⁴University of Washington Robust Multilingual Part-of-Speech Tagging via Adversarial Training Michihiro Yasunaga, Jungo Kasai, Dragomir Radev Yale University Towards a Variability Measure for Multiword Expressions Caroline Pasquer¹, Agata Savary¹, Jean-Yves Antoine¹, Carlos Ramisch² ¹University of Tours, ²Aix Marseille University Universal Dependency Parsing for Hindi-English Code-switching Irshad Bhat¹, Riyaz A. Bhat², Manish Shrivastava¹, Dipti Sharma¹ ¹International Institute of Information Technology, Hyderabad, ²Interaction Labs What's Going On in Neural Constituency Parsers? An Analysis David Gaddy, Mitchell Stern, Dan Klein University of California, Berkeley Madly Ambiguous: A Game for Learning about Structural Ambiguity and Why It's Hard for Computers (DEMO) Ajda Gokcen, Ethan Hill and Michael White VNCoreNLP: A Vietnamese Natural Language Processing Toolkit (DEMO) Thanh Vu, Dat Quoc Nguyen, Dai Quoc Nguyen, Mark Dras and Mark Johnson
11:30 - 12:30	Session Oral: Machine Learning 3 - Empire A Chair: Yulia Tsvetkov, Carnegie Mellon University
11:30AM - 11:48AM Deep Generative Model for Joint Alignment and Word Representation Miguel Rios, Wilker Aziz, Khalil Simaan University of Amsterdam 11:48AM - 12:06PM Evaluating the Stability of Embedding-based Word Similarities (TACL) Maria Antoniak and David Mimno 12:06PM - 12:24PM Learning Word Embeddings for Low-resource Languages by PU Learning Chao Jiang¹, Hsiang-Fu Yu², Cho-Jui Hsieh³, Kai-Wei Chang⁴ ¹University of Virginia, ²Amazon, ³University of California, Davis, ⁴University of California, Los Angeles
11:30 - 12:30	Session Oral: Social Media and Computational Social Science 2 - Empire B Chair: Nanyun Peng, University of Southern California / Information Sciences Institute
11:30AM - 11:48AM Exploring the Role of Prior Beliefs for Argument Persuasion Esin Durmus and Claire Cardie Cornell University 11:48AM - 12:06PM Inducing a Lexicon of Abusive Words -- a Feature-Based Approach Michael Wiegand¹, Josef Ruppenhofer², Anna Schmidt¹, Clayton Greenberg¹ ¹Saarland University, ²Institute for German Language 12:06PM - 12:24PM Author Commitment and Social Power: Automatic Belief Tagging to Infer the Social Context of Interactions Vinodkumar Prabhakaran¹, Premkumar Ganeshkumar², Owen Rambow³ ¹Stanford University, ²Agolo, Inc., ³Elemental Cognition, LLC
11:30 - 12:30	Session Oral: Vision, Robotics and Other Grounding 2 - Empire C Chair: Clare Voss, Army Research Lab
11:30AM - 11:48AM Defoiling Foiled Image Captions Pranava Swaroop Madhyastha, Josiah Wang, Lucia Specia University of Sheffield 11:48AM - 12:06PM Pragmatically Informative Image Captioning with Character-Level Inference Reuben Cohn-Gordon, Noah Goodman, Christopher Potts Stanford University 12:06PM - 12:24PM Object Ordering with Bidirectional Matchings for Visual Reasoning Hao Tan and Mohit Bansal University of North Carolina at Chapel Hill
11:30 - 12:30	[Industry Track] Session Oral: Named Entity and Language Generation - Empire D Chair: Christine Doran, Interactions LLC
11:30AM - 11:47AM Multi-lingual Neural Title Generation for E-Commerce Browse Pages Prashant Mathur, Nicola Ueffing, Gregor Leusch eBay 11:48AM - 12:05PM A Novel Approach to Part Name Discovery in Noisy Text Nobal Bikram Niraula, Daniel Whyatt, Anne Kao Boeing Research & Technology 12:05PM - 12:22PM The Alexa Meaning Representation Language Thomas Kollar¹, Danielle Berry¹, Lauren Stuart¹, Karolina Owczarzak¹, Tagyoung Chung², Lambert Mathias¹, Michael Kayser¹, Bradford Snow¹, Spyros Matsoukas¹ ¹Amazon, ²Amazon.com
12:30 - 14:00	Lunch
14:00 - 15:00	Industry Track Keynote 2 - Empire Ballroom Chair: Jennifer Chu-Carroll, Elemental Cognition
Building innovative startups, products, and services – personal insights Daniel Marcu, Amazon
15:00 - 15:30	Afternoon Coffee - Empire Foyer
15:30 - 17:00	Session Oral: Text Mining 1 - Empire A Chair: Kai-wei Chang, University of Virginia
3:30PM - 3:48PM Comparing Automatic and Human Evaluation of Local Explanations for Text Classification Dong Nguyen Alan Turing Institute 3:48PM - 4:06PM Deep Temporal-Recurrent-Replicated-Softmax for Topical Trends over Time Pankaj Gupta¹, Subburam Rajaram², Hinrich Schütze², Bernt Andrassy³ ¹Ludwig Maximilian University of Munich / Siemens, ²Ludwig Maximilian University of Munich, ³Siemens 4:06PM - 4:24PM Lessons from the Bible on Modern Topics: Low-Resource Multilingual Topic Model Evaluation Shudong Hao¹, Jordan Boyd-Graber², Michael J. Paul¹ ¹University of Colorado, Boulder, ²University of Maryland, College Park 4:24PM - 4:42PM Explainable Prediction of Medical Codes from Clinical Text James Mullenbach, Sarah Wiegreffe, Jon Duke, Jimeng Sun, Jacob Eisenstein Georgia Institute of Technology 4:43 PM - 5:00 PM Event Time Extraction with a Decision Tree of Neural Classifiers (TACL) Reimers, Nils and Dehghani, Nazanin and Gurevych, Iryna
15:30 - 17:00	Session Oral: Semantics 3 - Empire B Chair: Ido Dagan, Bar Ilan University
3:30PM - 3:48PM A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference Adina Williams, Nikita Nangia, Samuel Bowman New York University 3:48PM - 4:06PM Filling Missing Paths: Modeling Co-occurrences of Word Pairs and Dependency Paths for Recognizing Lexical Semantic Relations Koki Washio and Tsuneaki Kato The University of Tokyo 4:06PM - 4:24PM Specialising Word Vectors for Lexical Entailment Ivan Vulić¹ and Nikola Mrkšić² ¹University of Cambridge, ²PolyAI 4:24PM - 4:42PM Cross-lingual Abstract Meaning Representation Parsing Marco Damonte and Shay B. Cohen University of Edinburgh 4:43 PM - 5:00 PM Mapping to Declarative Knowledge for Word Problem Solving (TACL) Subhro Roy and Dan Roth
15:30 - 17:00	Session Oral: Tagging Chunking Syntax and Parsing 2 - Empire C Chair: Michael Collins, University of Columbia
3:30PM - 3:47PM Sentences with Gapping: Parsing and Reconstructing Elided Predicates Sebastian Schuster¹, Joakim Nivre², Christopher D. Manning¹ ¹Stanford University, ²Uppsala University 3:48PM - 4:06PM A Structured Syntax-Semantics Interface for English-AMR Alignment Ida Szubert¹, Adam Lopez¹, Nathan Schneider² ¹University of Edinburgh, ²Georgetown University 4:06PM - 4:24PM End-to-end Graph-based TAG Parsing with Neural Networks Jungo Kasai¹, Robert Frank¹, Pauli Xu¹, William Merrill¹, Owen Rambow² ¹Yale University, ²Elemental Cognition, LLC 4:24PM - 4:42PM Colorless Green Recurrent Networks Dream Hierarchically Kristina Gulordava¹, Piotr Bojanowski², Edouard Grave², Tal Linzen³, Marco Baroni² ¹University of Geneva, ²Facebook AI Research, ³Johns Hopkins University 4:43 PM - 5:00 PM Knowledge Completion for Generics using Guided Tensor Factorization (TACL) Hanie Sedghi, Ashish Sabharwal
15:30 - 17:00	Ethics in NLP Panel - Empire D Chair: Dirk Hovy, Universita Bocconi
14:00 - 15:30	Session Posters and Demos: Phonology Morphology and Word Segmentation 2 - Elite Hall B Chair: TBD
Are All Languages Equally Hard to Language-Model? Ryan Cotterell¹, Sebastian J. Mielke¹, Jason Eisner¹, Brian Roark² ¹Johns Hopkins University, ²Google Context Sensitive Neural Lemmatization with Lematus Toms Bergmanis and Sharon Goldwater University of Edinburgh Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media Gustavo Aguilar¹, Adrian Pastor López Monroy¹, Fabio González², Thamar Solorio¹ ¹University of Houston, ²Universidad Nacional de Colombia Reusing Weights in Subword-aware Neural Language Models Zhenisbek Assylbekov and Rustem Takhanov Nazarbayev University Simple Models for Word Formation in Slang Vivek Kulkarni and William Yang Wang University of California, Santa Barbara The Computational Complexity of Distinctive Feature Minimization in Phonology Hubie Chen¹ and Mans Hulden² ¹Birkbeck, University of London, ²University of Colorado, Boulder Unsupervised Disambiguation of Syncretism in Inflected Lexicons Ryan Cotterell, Christo Kirov, Sebastian J. Mielke, Jason Eisner Johns Hopkins University Using Morphological Knowledge in Open-Vocabulary Neural Language Models Austin Matthews¹, Graham Neubig¹, Chris Dyer² ¹Carnegie Mellon University, ²DeepMind
15:30 - 17:00	Session Posters and Demos: Machine Learning 4 - Elite Hall B Chair: TBD
Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations Sosuke Kobayashi Preferred Networks, Inc. Cross-lingual Learning-to-Rank with Shared Representations Shota Sasaki¹, Shuo Sun², Shigehiko Schamoni³, Kevin Duh², Kentaro Inui⁴ ¹Tohoku University, ²Johns Hopkins University, ³Heidelberg University, ⁴Tohoku University / RIKEN AIP Diverse Few-Shot Text Classification with Multiple Metrics Mo Yu, Xiaoxiao Guo, Jinfeng Yi, Shiyu Chang, Saloni Potdar, Yu Cheng, Gerald Tesauro, Haoyu Wang, Bowen Zhou IBM Research Early Text Classification Using Multi-Resolution Concept Representations Adrian Pastor López Monroy¹, Fabio A. González², Manuel Montes³, Hugo Jair Escalante³, Thamar Solorio¹ ¹University of Houston, ²Universidad Nacional de Colombia, ³Instituto Nacional de Astrofísica, Óptica y Electrónica Embedding Syntax and Semantics of Prepositions via Tensor Decomposition Hongyu Gong, Suma Bhat, Pramod Viswanath University of Illinois at Urbana Champaign Multinomial Adversarial Networks for Multi-Domain Text Classification Xilun Chen and Claire Cardie Cornell University Pivot Based Language Modeling for Improved Neural Domain Adaptation Yftah Ziser and Roi Reichart Technion Reinforced Co-Training Jiawei Wu¹, Lei Li², William Yang Wang¹ ¹University of California, Santa Barbara, ²Toutiao AI Lab Self-Attention with Relative Position Representations Peter Shaw, Jakob Uszkoreit, Ashish Vaswani Google Tensor Product Generation Networks for Deep NLP Modeling Qiuyuan Huang¹, Paul Smolensky¹, Xiaodong He², Li Deng¹, Dapeng Wu³ ¹Microsoft Research, ²JD AI Research, ³University of Florida Text Segmentation as a Supervised Learning Task Omri Koshorek, Adir Cohen, Noam Mor, Michael Rotman, Jonathan Berant Tel Aviv University The Context-dependent Additive Recurrent Neural Net Quan Hung Tran¹, Tuan Lai², Gholamreza Haffari³, Ingrid Zukerman³, Trung Bui², Hung Bui⁴ ¹Monash University / Adobe Research, ²Adobe Research, ³Monash University, ⁴DeepMind What's in a Domain? Learning Domain-Robust Text Representations using Adversarial Training Yitong Li, Timothy Baldwin, Trevor Cohn The University of Melbourne CNNs for NLP in the Browser: Client-Side Deployment and Visualization Opportunities (DEMO) Yiyun Liang, Zhucheng Tu, Laetitia Huang and Jimmy Lin Generating Continuous Representations of Medical Texts (DEMO) Graham Spinks and Marie-Francine Moens ListOps: A Diagnostic Dataset for Latent Tree Learning (SRW) Nikita Nangia and Samuel Bowman Neural Lattice Language Models (TACL) Jacob Buckman and Graham Neubig
15:30 - 17:00	Session Posters and Demos: Machine Translation 2 - Elite Hall B Chair: TBD
Automated Paraphrase Lattice Creation for HyTER Machine Translation Evaluation Marianna Apidianaki¹, Guillaume Wisniewski², Anne Cocos³, Chris Callison-Burch³ ¹University of Pennsylvania / LIMSI, CNRS, ²LIMSI, CNRS, ³University of Pennsylvania Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention Huadong Chen¹, Shujian Huang¹, David Chiang², Xinyu Dai¹, Jiajun Chen¹ ¹Nanjing University, ²University of Notre Dame Dense Information Flow for Neural Machine Translation Yanyao Shen¹, Xu Tan², Di He³, Tao Qin², Tie-Yan Liu² ¹The University of Texas at Austin, ²Microsoft Research Asia, ³Peking University Evaluating Discourse Phenomena in Neural Machine Translation Rachel Bawden¹, Rico Sennrich², Alexandra Birch³, Barry Haddow³ ¹LIMSI, CNRS, ²University of Edinburgh / University of Zurich, ³University of Edinburgh Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks Diego Marcheggiani¹, Joost Bastings², Ivan Titov¹ ¹University of Edinburgh / University of Amsterdam, ²University of Amsterdam Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation Matt Post and David Vilar Amazon Guiding Neural Machine Translation with Retrieved Translation Pieces Jingyi Zhang¹, Masao Utiyama², Eiichro Sumita², Graham Neubig³, Satoshi Nakamura⁴ ¹National Institute of Information and Communications Technology / Nara Institute of Science and Technology, ²National Institute of information and Communications Technology, ³Carnegie Mellon University, ⁴Nara Institute of Science and Technology Handling Homographs in Neural Machine Translation Frederick Liu, Han Lu, Graham Neubig Carnegie Mellon University Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets Zhen Yang, Wei Chen, Feng Wang, Bo Xu Chinese Academy of Sciences Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Stephan Vogel Qatar Computing Research Institute Learning Hidden Unit Contribution for Adapting Neural Machine Translation Models David Vilar Amazon Neural Machine Translation Decoding with Terminology Constraints Eva Hasler¹, Adrià de Gispert², Gonzalo Iglesias¹, Bill Byrne² ¹SDL Research, ²SDL Research / University of Cambridge Neural Machine Translation for Bilingually Scarce Scenarios: a Deep Multi-task Learning Approach Poorya Zaremoodi and Gholamreza Haffari Monash University On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference Adam Poliak¹, Yonatan Belinkov², James Glass², Benjamin Van Durme¹ ¹Johns Hopkins University, ²Massachusetts Institute of Technology Self-Attentive Residual Decoder for Neural Machine Translation Lesly Miculicich Werlen¹, Nikolaos Pappas², Dhananjay Ram¹, Andrei Popescu-Belis³ ¹École Polytechnique Fédérale de Lausanne / Idiap Research Institute, ²Idiap Research Institute, ³HEIG-VD / HES-SO Target Foresight Based Attention for Neural Machine Translation Xintong Li¹, Lemao Liu², Zhaopeng Tu², Shuming Shi², Max Meng¹ ¹The Chinese University of Hong Kong, ²Tencent AI Lab Using Word Vectors to Improve Word Alignments for Low Resource Machine Translation Nima Pourdamghani, Marjan Ghazvininejad, Kevin Knight University of Southern California / Information Sciences Institute When and Why Are Pre-trained Word Embeddings Useful for Neural Machine Translation? Ye Qi, Devendra Sachan, Matthieu Felix, Sarguna Padmanabhan, Graham Neubig Carnegie Mellon University VisMet: A Multi-Metric Tool for Evaluating and Inspecting Machine Translation Output (DEMO) David Steele and Lucia Specia Japanese Predicate Conjugation for Neural Machine Translation (SRW) Michiki Kurosawa, Yukio Matsumura, Hayahide Yamagishi and Mamoru Komachi Metric for Automatic Machine Translation Evaluation based on Universal Sentence Representations (SRW) Hiroki Shimanaka, Tomoyuki Kajiwara and Mamoru Komachi Neural Machine Translation for Low Resource Languages using Bilingual Lexicon Induced from Comparable Corpora (SRW) Sree Harsha Ramesh and Krishna Prasad Sankaranarayanan
15:30 - 17:00	[Industry] Session Posters and Demos: Machine Learning - Elite Hall B Chair: TBD
Practical Application of Domain Dependent Confidence Measurement for Spoken Language Understanding Systems Mahnoosh Mehrabani, David Thomson, Benjamin Stern Interactions LLC
15:30 - 17:00	[Industry] Session Posters and Demos: Machine Translation - Elite Hall B Chair: TBD
Document-based Recommender System for Job Postings using Dense Representations Ahmed Elsafty¹, Martin Riedl², Chris Biemann³ ¹XING SE, ²University of Stuttgart, ³University of Hamburg
17:15 - 18:30	Test of Time Session (in honor of Aravind Joshi) - Empire B Chair: Marilyn Walker, University of California, Santa Cruz
5:15 PM - 5:40 PM BLEU: a Method for Automatic Evaluation of Machine Translation Kishore Papineni, Salim Roukos, Todd Ward and Wei-Jing Zhu, IBM Research 5:40 PM - 6:05 PM Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms Michael Collins, Columbia University 6:05 PM - 6:30 PM Thumbs up?: Sentiment Classification using Machine Learning Techniques Bo Pang, Lillian Lee, Shivakumar Vaithyanathan, Cornell University, IBM Research

Monday, June 4
07:45 - 08:45	Breakfast - Empire Foyer
08:45 - 09:00	Announcements - Empire Ballroom Chair: Marilyn Walker, University of California, Santa Cruz
09:00 - 10:00	Keynote 3 (sponsored by Bloomberg) - Empire Ballroom Chair: Heng Ji, Rensselaer Polytechnic Institute
Google Assistant or My Assistant? Towards Personalized Situated Conversational Agents Dilek Hakkani-Tür, Google
10:00 - 10:30	Morning Coffee - Empire Foyer
10:30 - 11:30	Session Oral: Information Extraction 4 - Empire A Chair: Bonan Min, Raytheon BBN Technologies
10:30AM - 10:47AM A Neural Layered Model for Nested Named Entity Recognition Meizhi Ju¹, Makoto Miwa², Sophia Ananiadou¹ ¹University of Manchester / National Institute of Advanced Industrial Science and Technology (AIST), ²Toyota Technological Institute / National Institute of Advanced Industrial Science and Technology (AIST) 10:48AM - 11:06AM DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference Reza Ghaeini¹, Sadid A. Hasan², Vivek Datla², Joey Liu², Kathy Lee², Ashequl Qadir², Yuan Ling², Aaditya Prakash², Xiaoli Fern¹, Oladimeji Farri² ¹Oregon State University, ²Philips Research North America 11:06AM - 11:24AM KBGAN: Adversarial Learning for Knowledge Graph Embeddings LiLiwei Cai¹ and William Yang Wang² ¹Tsinghua University, ²University of California, Santa Barbara
10:30 - 11:30	Session Oral: Semantics 4 - Empire B Chair: Yaser Al-Onaizan, Amazon
10:30AM - 10:47AM Multimodal Frame Identification with Multilingual Evaluation Teresa Botschen, Iryna Gurevych, Jan-Christoph Klie, Hatem Mousselly Sergieh, Stefan Roth Technische Universität Darmstadt 10:48AM - 11:06AM Learning Joint Semantic Parsers from Disjoint Data Hao Peng¹, Sam Thomson², Swabha Swayamdipta², Noah A. Smith¹ ¹University of Washington, ²Carnegie Mellon University 11:06AM - 11:24AM Identifying Semantic Divergences in Parallel Text without Annotations Yogarshi Vyas, Xing Niu, Marine Carpuat University of Maryland, College Park
10:30 - 11:30	Session Oral: Generation 2 - Empire C Chair: Michael White, Ohio State University
10:30AM - 10:48AM Bootstrapping Generators from Noisy Data Laura Perez-Beltrachini and Mirella Lapata University of Edinburgh 10:48AM - 11:06AM SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation Ye Zhang¹, Nan Ding², Radu Soricut² ¹The University of Texas at Austin, ²Google 11:06AM - 11:24AM Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization Preksha Nema¹, Shreyas Shetty¹, Parag Jain², Anirban Laha², Karthik Sankaranarayanan², Mitesh M. Khapra¹ ¹Indian Institute of Technology, Madras, ²IBM Research
10:30 - 12:00	Session Posters and Demos: Question Answering 2 - Elite Hall B Chair: Lu Wang, Northeastern University
CliCR: a Dataset of Clinical Case Reports for Machine Reading Comprehension Simon Suster and Walter Daelemans University of Antwerp Contextualized Word Representations for Reading Comprehension Shimi Salant and Jonathan Berant Tel Aviv University Crowdsourcing Question-Answer Meaning Representations Julian Michael¹, Gabriel Stanovsky², Luheng He¹, Ido Dagan³, Luke Zettlemoyer¹ ¹University of Washington, ²University of Washington / Allen Institute for Artificial Intelligence, ³Bar-Ilan University Learning to Collaborate for Question Answering and Asking Duyu Tang¹, Nan Duan¹, Zhao Yan², Zhirui Zhang³, Yibo Sun⁴, Shujie Liu¹, Yuanhua Lv⁵, Ming Zhou¹ ¹Microsoft Research Asia, ²Beihang University, ³University of Science and Technology of China, ⁴Harbin Institute of Technology, ⁵Microsoft AI and Research Learning to Rank Question-Answer Pairs Using Hierarchical Recurrent Encoder with Latent Topic Clustering Seunghyun Yoon, Joongbo Shin, Kyomin Jung Seoul National University Leveraging Context Information for Natural Question Generation Linfeng Song¹, Zhiguo Wang², Wael Hamza², Yue Zhang³, Daniel Gildea¹ ¹University of Rochester, ²IBM Research, ³Singapore University of Technology and Design Robust Machine Comprehension Models via Adversarial Training Yicheng Wang and Mohit Bansal University of North Carolina at Chapel Hill Simple and Effective Semi-Supervised Question Answering Bhuwan Dhingra, Danish Danish, Dheeraj Rajagopal Carnegie Mellon University Supervised and Unsupervised Transfer Learning for Question Answering Yu-An Chung¹, Hung-yi Lee², James Glass¹ ¹Massachusetts Institute of Technology, ²National Taiwan University Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension Bhavana Dalvi¹, Lifu Huang², Niket Tandon¹, Wen-tau Yih¹, Peter Clark¹ ¹Allen Institute for Artificial Intelligence, ²Rensselaer Polytechnic Institute TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation Tao Yu, Zifan Li, Zilin Zhang, Rui Zhang, Dragomir Radev Yale University Training a Ranking Function for Open-Domain Question Answering (SRW) Phu Mon Htut, Samuel Bowman and Kyunghyun Cho
10:30 - 12:00	Session Posters and Demos: Social Media and Computational Social Science 3 - Elite Hall B Chair: Lu Wang, Northeastern University
Combining Deep Learning and Topic Modeling for Review Understanding in Context-Aware Recommendation Mingmin Jin¹, Xin Luo¹, Huiling Zhu², Hankz Hankui Zhuo² ¹Sun Yat-sen University, ²Sun Yat-sen University / Guangdong Key Laboratory of Big Data Analysis and Processing Community Member Retrieval on Social Media Using Textual Information Aaron Jaech, Shobhit Hathi, Mari Ostendorf University of Washington Cross-Domain Review Helpfulness Prediction Based on Convolutional Neural Networks with Auxiliary Domain Discriminators Cen Chen¹, Yinfei Yang², Jun Zhou¹, Xiaolong Li¹, Forrest Sheng Bao³ ¹Ant Financial Services Group, ²Google, ³Iowa State Univerity Deconfounded Lexicon Induction for Interpretable Social Science Reid Pryzant, Kelly Shen, Dan Jurafsky, Stefan Wagner Stanford University Detecting Denial-of-Service Attacks from Social Media Text: Applying NLP to Computer Security Nathanael Chambers, Ben Fry, James McMasters US Naval Academy Predicting Foreign Language Usage from English-Only Social Media Posts Svitlana Volkova, Stephen Ranshous, Lawrence Phillips Pacific Northwest National Laboratory The Importance of Calibration for Estimating Proportions from Annotations Dallas Card¹ and Noah A. Smith² ¹Carnegie Mellon University, ²University of Washington Know Who Your Friends Are: Understanding Social Connections from Unstructured Text (DEMO) Lea Deleris, Francesca Bonin, Elizabeth Daly, Stephane Deparis, Yufang Hou, Charles Jochim, Yassine Lassoued and Killian Levacher Corpus Creation and Emotion Prediction for Hindi-English Code-Mixed Social Media Text (SRW) Deepanshu Vijay, Aditya Bohra, Vinay Singh, Syed Sarfaraz Akhtar and Manish Shrivastava
10:30 - 12:00	Session Posters and Demos: Summarization 2 - Elite Hall B Chair: Lu Wang, Northeastern University
A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications Dongyeop Kang¹, Waleed Ammar², Bhavana Dalvi², Madeleine van Zuylen², Sebastian Kohlmeier², Eduard Hovy¹, Roy Schwartz³ ¹Carnegie Mellon University, ²Allen Institute for Artificial Intelligence, ³University of Washington / The Allen Institute for Artificial Intelligence A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents Arman Cohan¹, Franck Dernoncourt², Doo Soon Kim², Trung Bui², Seokhwan Kim², Walter Chang², Nazli Goharian¹ ¹Georgetown University, ²Adobe Research A Mixed Hierarchical Attention Based Encoder-Decoder Approach for Standard Table Summarization Parag Jain¹, Anirban Laha¹, Karthik Sankaranarayanan¹, Preksha Nema², Mitesh M. Khapra², Shreyas Shetty² ¹IBM Research, ²Indian Institute of Technology, Madras Deep Communicating Agents for Abstractive Summarization Asli Celikyilmaz¹, Antoine Bosselut², Xiaodong He³, Yejin Choi⁴ ¹Microsoft Research, ²University of Washington, ³JD AI Research, ⁴University of Washington / Allen Institute for Artificial Intelligence Effective Crowdsourcing for a New Type of Summarization Task Youxuan Jiang, Catherine Finegan-Dollak, Jonathan K. Kummerfeld, Walter Lasecki University of Michigan Encoding Conversation Context for Neural Keyphrase Extraction from Microblog Posts Yingyi Zhang¹, Jing Li², Yan Song², Chengzhi Zhang¹ ¹Nanjing University of Science and Technology, ²Tencent AI Lab Estimating Summary Quality with Pairwise Preferences Markus Zopf Technische Universität Darmstadt Generating Topic-oriented Summaries Using Neural Attention Kundan Krishna and Balaji Vasan Srinivasan Adobe Research Generative Bridging Network for Neural Sequence Prediction Wenhu Chen¹, Guanlin Li², Shuo Ren³, Shujie Liu⁴, Zhirui Zhang⁵, Mu Li⁴, Ming Zhou⁴ ¹University of California, Santa Barbara, ²Harbin Institute of Technology, ³Beijing University of Aeronautics and Astronautics, ⁴Microsoft Research Asia, ⁵University of Science and Technology of China Higher-order Syntactic Attention Network for Longer Sentence Compression Hidetaka Kamigaito¹, Katsuhiko Hayashi², Tsutomu Hirao³, Masaaki Nagata³ ¹Tokyo Institute of Technology, ²Osaka University, ³NTT Communication Science Laboratories Key2Vec: Automatic Ranked Keyphrase Extraction from Scientific Articles using Phrase Embeddings Debanjan Mahata¹, John Kuriakose², Rajiv Ratn Shah³, Roger Zimmermann⁴ ¹Bloomberg, ²Infosys Limited, ³Indraprastha Institute of Information Technology, Delhi, ⁴National University of Singapore Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata Lucie-Aimée Kaffee¹, Hady Elsahar², Pavlos Vougiouklis¹, Christophe Gravier², Frederique Laforest², Jonathon Hare¹, Elena Simperl¹ ¹University of Southampton, ²Université de Lyon Multi-Reward Reinforced Summarization with Saliency and Entailment Ramakanth Pasunuru and Mohit Bansal University of North Carolina at Chapel Hill Neural Storyline Extraction Model for Storyline Generation from News Articles Deyu Zhou¹, Linsen Guo¹, Yulan He² ¹Southeast University, ²Aston University Objective Function Learning to Match Human Judgements for Optimization-Based Summarization Maxime Peyrard and Iryna Gurevych Technische Universität Darmstadt Provable Fast Greedy Compressive Summarization with Any Monotone Submodular Function Shinsaku Sakaue, Tsutomu Hirao, Masaaki Nishino, Masaaki Nagata NTT Communication Science Laboratories Pruning Basic Elements for Better Automatic Evaluation of Summaries Ukyo Honda¹, Tsutomu Hirao², Masaaki Nagata² ¹Nara Institute of Science and Technology, ²NTT Communication Science Laboratories Ranking Sentences for Extractive Summarization with Reinforcement Learning Shashi Narayan, Shay B. Cohen, Mirella Lapata University of Edinburgh Relational Summarization for Corpus Analysis Abram Handler and Brendan O'Connor University of Massachusetts, Amherst Unsupervised Keyphrase Extraction with Multipartite Graphs Florian Boudin Université de Nantes What's this Movie about? A Joint Neural Network Architecture for Movie Content Analysis Philip John Gorinski and Mirella Lapata University of Edinburgh Where Have I Heard This Story before?: Identifying Narrative Similarity in Movie Remakes Snigdha Chaturvedi¹, Shashank Srivastava², Dan Roth³ ¹University of California, Santa Cruz, ²Carnegie Mellon, ³University of Pennsylvania Which Scores to Predict in Sentence Regression for Text Summarization? Markus Zopf, Eneldo Loza Mencía, Johannes Fürnkranz Technische Universität Darmstadt RiskFinder: A Sentence-Level Risk Detector for Financial Reports (DEMO) Yu-Wen Liu, Liang-Chih Liu, Chuan-Ju Wang and Ming-Feng Tsai
11:30 - 12:30	Session Oral: Dialogue and Interactive Systems 1 - Empire A Chair: Yun-Nung (Vivian) Chen, National Taiwan University
11:30AM - 11:48AM A Hierarchical Latent Structure for Variational Conversation Modeling Yookoon Park, Jaemin Cho, Gunhee Kim Seoul National University 11:48AM - 12:06PM Detecting Egregious Conversations between Customers and Virtual Agents Tommy Sandbank, Michal Shmueli-Scheuer, Jonathan Herzig, David Konopnicki, John Richards, David Piorkowski IBM Research 12:06PM - 12:24PM Learning to Disentangle Interleaved Conversational Threads with a Siamese Hierarchical Network and Similarity Ranking Jyun-Yu Jiang¹, Francine Chen², Yan-Ying Chen², Wei Wang¹ ¹University of California, Los Angeles, ²FXPAL
11:30 - 12:30	Session Oral: Information Extraction 5 - Empire B Chair: Xiang Ren, University of Southern California / Information Sciences Institute
10:30AM - 10:48AM Variational Knowledge Graph Reasoning Wenhu Chen, Wenhan Xiong, Xifeng Yan, William Yang Wang University of California, Santa Barbara 10:48AM - 11:06AM Inducing Temporal Relations from Time Anchor Annotation Fei Cheng and Yusuke Miyao National Institute of Informatics 11:06AM - 11:24AM ELDEN: Improved Entity Linking Using Densified Knowledge Graphs Priya Radhakrishnan¹, Partha Talukdar², Vasudeva Varma¹ ¹International Institute of Information Technology, Hyderabad, ²Indian Institute of Science
11:30 - 12:30	Session Oral: Generation 3 - Empire C Chair: Amanda Stent, Bloomberg
11:30AM - 11:48AM Interpretable Charge Predictions for Criminal Cases: Learning to Generate Court Views from Fact Descriptions Hai Ye¹, Xin Jiang¹, Zhunchen Luo², Wenhan Chao¹ ¹Beihang University, ²PLA Academy of Military Science 11:48AM - 12:06PM Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer Juncen Li¹, Robin Jia², He He², Percy Liang² ¹Tencent, ²Stanford University 12:06PM - 12:24PM Adversarial Example Generation with Syntactically Controlled Paraphrase Networks Mohit Iyyer¹, John Wieting², Kevin Gimpel³, Luke Zettlemoyer⁴ ¹Allen Institute for Artificial Intelligence / University of Massachusetts, Amherst, ²Carnegie Mellon University, ³Toyota Technological Institute at Chicago, ⁴University of Washington
11:30 - 12:30	[Industry Track] Session Oral: Machine Learning - Prediction - Empire D Chair: Gokhan Tur, Uber
11:30AM - 11:47AM Prediction for the Newsroom: Which Articles Will Get the Most Comments? Carl Ambroselli¹, Julian Risch¹, Ralf Krestel¹, Andreas Loos² ¹Hasso Plattner Institute, University of Potsdam, ²ZEIT ONLINE 11:48AM - 12:05PM Demand-Weighted Completeness Prediction for a Knowledge Base Andrew Hopkinson¹, Amit Gurdasani¹, Dave Palfrey¹, Arpit Mittal² ¹Amazon Research Cambridge, ²Amazon 12:05PM - 12:22PM Personalized neural language models for real-world query auto completion Nicolas Fiorini and Zhiyong Lu NCBI/NLM/NIH
12:30 - 14:00	Lunch
13:00 - 14:00	NAACL Business Meeting Julia Hockenmaier, University of Illinois at Urbana-Champaign
14:00 - 15:30	Session Oral: Sentiment Analysis 2 - Empire A Chair: Smaranda Muresan, Columbia University
2:00PM - 2:18PM Sentiment Analysis: It’s Complicated! Kian Kenyon-Dean, Eisha Ahmed, Scott Fujimoto, Jeremy Georges-Filteau, Christopher Glasz, Barleen Kaur, Auguste Lalande, Shruti Bhanderi, Robert Belfer, Nirmal Kanagasabai, Roman Sarrazingendron, Rohit Verma, Derek Ruths McGill University 2:18PM - 2:36PM Multi-task Learning of Pairwise Sequence Classification Tasks over Disparate Label Spaces Isabelle Augenstein¹, Sebastian Ruder², Anders Søgaard¹ ¹University of Copenhagen, ²National University of Ireland, Galway / Aylien Ltd. 2:36PM - 2:54PM Word Emotion Induction for Multiple Languages as a Deep Multi-Task Learning Problem Sven Buechel and Udo Hahn Friedrich-Schiller-Universität Jena 2:54PM - 3:12PM Human Needs Categorization of Affective Events Using Labeled and Unlabeled Data Haibo Ding and Ellen Riloff University of Utah 3:13PM - 3:30PM Multimodal Emoji Prediction Francesco Barbieri¹, Miguel Ballesteros², Francesco Ronzano¹, Horacio Saggion¹ ¹Universitat Pompeu Fabra, ²IBM Research
14:00 - 15:30	Session Oral: Discourse and Pragmatics 2 - Empire B Chair: Vincent Ng, The University of Texas at Dallas
2:00PM - 2:18PM The Argument Reasoning Comprehension Task: Identification and Reconstruction of Implicit Warrants Ivan Habernal¹, Henning Wachsmuth², Iryna Gurevych¹, Benno Stein² ¹Technische Universität Darmstadt, ²Bauhaus-Universität Weimar 2:18PM - 2:36PM Linguistic Cues to Deception and Perceived Deception in Interview Dialogues Sarah Ita Levitan, Angel Maredia, Julia Hirschberg Columbia University 2:36PM - 2:54PM Unified Pragmatic Models for Generating and Following Instructions Daniel Fried, Jacob Andreas, Dan Klein University of California, Berkeley 2:54PM - 3:12PM Hierarchical Structured Model for Fine-to-coarse Manifesto Text Analysis Shivashankar Subramanian, Trevor Cohn, Timothy Baldwin University of Melbourne 3:13PM - 3:30PM Higher-order Coreference Resolution with Coarse-to-fine Inference Kenton Lee, Luheng He, Luke Zettlemoyer University of Washington
14:00 - 15:30	Session Oral: Tagging Chunking Syntax and Parsing 3 - Empire C Chair: Thamar Solorio, University of Houston
2:00PM - 2:18PM Do latent tree learning models identify meaningful structure in sentences? (TACL) Adina Williams, Andrew Drozdov, Samuel R. Bowman 2:18 PM - 2:36 PM Unsupervised Acquisition of Comprehensive Multiword Lexicons using Competition in an N-Gram Lattice (TACL) Julian Brooke, Jan Šnajder, and Timothy Baldwin 2:36 PM - 2:53 PM Unsupervised Grammar Induction with Depth-bounded PCFG (TACL) Lifeng Jin; Finale Doshi-Velez; Timothy Miller; William Schuler; Lane Schwartz 2:54PM - 3:12PM Non-Projective Dependency Parsing with Non-Local Transitions Daniel Fernández-González and Carlos Gómez-Rodríguez Universidade da Coruña 3:12PM - 3:30PM Behavior Analysis of NLI Models: Uncovering the Influence of Three Factors on Robustness Ivan Sanchez, Jeff Mitchell, Sebastian Riedel University College London
14:00 - 15:30	Session Posters and Demos: Cognitive Modeling and Psycholinguistics 2 - Elite Hall B Chair: Hannaneh Hajishirzi, University of Washington
Assessing Language Proficiency from Eye Movements in Reading Yevgeni Berzak, Boris Katz, Roger Levy Massachusetts Institute of Technology Comparing Theories of Speaker Choice Using a Model of Classifier Production in Mandarin Chinese Meilin Zhan and Roger Levy Massachusetts Institute of Technology Detecting Linguistic Characteristics of Alzheimer's Dementia by Interpreting Neural Models Sweta Karlekar, Tong Niu, Mohit Bansal University of North Carolina at Chapel Hill Spotting Spurious Data with Neural Networks Hadi Amiri, Timothy Miller, Guergana Savova Boston Children's Hospital Informatics Program The Timing of Lexical Memory Retrievals in Language Production Jeremy Cole and David Reitter The Pennsylvania State University Unsupervised Induction of Linguistic Categories with Records of Reading, Speaking, and Writing Maria Barrett¹, Ana Valeria Gonzalez-Garduño¹, Lea Frermann², Anders Søgaard¹ ¹University of Copenhagen, ²Amazon Sensing and Learning Human Annotators Engaged in Narrative Sensemaking (SRW) McKenna Tornblad, Luke Lapresi, Raymond Ptucha, Christopher Homan and Cecilia Ovesdotter Alm
14:00 - 15:30	Session Posters and Demos: Dialogue and Interactive Systems - Elite Hall B Chair: Hannaneh Hajishirzi, University of Washington
Challenging Reading Comprehension on Daily Conversation: Passage Completion on Multiparty Dialog Kaixin Ma, Tomasz Jurczyk, Jinho D. Choi Emory University Deep Dungeons and Dragons: Learning Character-Action Interactions from Role-Playing Game Transcripts Annie Louis and Charles Sutton University of Edinburgh Dialog Generation Using Multi-turn Reasoning Neural Networks Xianchao Wu¹, Ander Martinez², Momo Klyen¹ ¹Microsoft Development Co., Ltd., ²National Institute of Advanced Industrial Science and Technology Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems Bing Liu¹, Gokhan Tür², Dilek Hakkani-Tür², Pararth Shah², Larry Heck³ ¹Carnegie Mellon University, ²Google Research, ³Samsung Research Feudal Reinforcement Learning for Dialogue Management in Large Domains Iñigo Casanueva¹, Paweł Budzianowski¹, Pei-Hao Su², Stefan Ultes¹, Lina M. Rojas Barahona¹, Bo-Hsiang Tseng¹, Milica Gasic¹ ¹University of Cambridge, ²PolyAI LSDSCC: a Large Scale Domain-Specific Conversational Corpus for Response Generation with Diversity Oriented Evaluation Metrics Zhen Xu¹, Nan Jiang², Bingquan Liu¹, Wenge Rong², Bowen Wu³, Baoxun Wang³, Zhuoran Wang³, Xiaolong Wang¹ ¹Harbin Institute of Technology, ²Beihang University, ³Tricorn (Beijing) Technology Co., Ltd. Decision Conversations Decoded (DEMO) Lea Deleris, Debasis Ganguly, Killian Levacher, Martin Stephenson and Francesca Bonin Sounding Board: A User-Centric and Content-Driven Social Chatbot (DEMO) Hao Fang, Hao Cheng, Maarten Sap, Elizabeth Clark, Ari Holtzman, Yejin Choi, Noah A. Smith and Mari Ostendorf
15:00 - 15:30	Session Posters and Demos: Text Mining 2 - Elite Hall B Chair: Hannaneh Hajishirzi, University of Washington
EMR Coding with Semi-Parametric Multi-Head Matching Networks Anthony Rios and Ramakanth Kavuluru University of Kentucky Evaluating Historical Text Normalization Systems: How Well Do They Generalize? Alexander Robertson and Sharon Goldwater University of Edinburgh Factors Influencing the Surprising Instability of Word Embeddings Laura Wendlandt, Jonathan K. Kummerfeld, Rada Mihalcea University of Michigan Gated Multi-Task Network for Text Classification Liqiang Xiao, Honglun Zhang, Wenqing Chen Shanghai Jiao Tong University Mining Evidences for Concept Stock Recommendation Qi Liu and Yue Zhang Singapore University of Technology and Design Natural Language to Structured Query Generation via Meta-Learning Po-Sen Huang¹, Chenglong Wang², Rishabh Singh¹, Wen-tau Yih³, Xiaodong He⁴ ¹Microsoft Research, ²University of Washington, ³Allen Institute for Artificial Intelligence, ⁴JD AI Research Smaller Text Classifiers with Discriminative Cluster Embeddings Mingda Chen and Kevin Gimpel Toyota Technological Institute at Chicago
14:00 - 15:30	Session Posters and Demos: Speech 2 - Elite Hall B Chair: Hannaneh Hajishirzi, University of Washington
Binarized LSTM Language Model Xuan Liu, Di Cao, Kai Yu Shanghai Jiao Tong University Conversational Memory Network for Emotion Recognition in Dyadic Dialogue Videos Devamanyu Hazarika¹, Soujanya Poria², Amir Zadeh³, Erik Cambria⁴, Louis-Philippe Morency³, Roger Zimmermann¹ ¹National University of Singapore, ²ASTAR, ³Carnegie Mellon University, ⁴Nanyang Technological University How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogues* Shang-Yu Su, Pei-Chieh Yuan, Yun-Nung Chen National Taiwan University Role-specific Language Models for Processing Recorded Neuropsychological Exams Tuka Al Hanai¹, Rhoda Au², James Glass¹ ¹Massachusetts Institute of Technology, ²Boston University School of Medicine and Public Health / The Framingham Heart Study Slot-Gated Modeling for Joint Slot Filling and Intent Prediction Chih-Wen Goo¹, Guang Gao¹, Yun-Kai Hsu², Chih-Li Huo², Tsung-Chieh Chen², Keng-Wei Hsu², Yun-Nung Chen¹ ¹National Taiwan University, ²Institute for Information Industry Towards Understanding Text Factors in Oral Reading Anastassia Loukina, Van Rynald T. Liceralde, Beata Beigman Klebanov Educational Testing Service
14:00 - 15:30	Session Posters and Demos: Vision, Robotics and Other Grounding 3 - Elite Hall B Chair: Hannaneh Hajishirzi, University of Washington
An Evaluation of Image-based Verb Prediction Models against Human Eye-tracking Data Spandana Gella and Frank Keller University of Edinburgh Generating Bilingual Pragmatic Color References Will Monroe¹, Jennifer Hu², Andrew Jong³, Christopher Potts¹ ¹Stanford University, ²Harvard University, ³San Jose State University Learning to Color from Language Varun Manjunatha¹, Mohit Iyyer², Jordan Boyd-Graber¹, Larry Davis¹ ¹University of Maryland, College Park, ²Allen Institute for Artificial Intelligence / University of Massachusetts, Amherst Learning with Latent Language Jacob Andreas, Dan Klein, Sergey Levine University of California, Berkeley Object Counts! Bringing Explicit Detections Back into Image Captioning Josiah Wang, Pranava Swaroop Madhyastha, Lucia Specia University of Sheffield Punny Captions: Witty Wordplay in Image Descriptions Arjun Chandrasekaran¹, Devi Parikh², Mohit Bansal³ ¹Georgia Institute of Technology, ²Georgia Institute of Technology / Facebook AI Research, ³University of North Carolina at Chapel Hill Quantifying the Visual Concreteness of Words and Topics in Multimodal Datasets Jack Hessel, David Mimno, Lillian Lee Cornell University Speaker Naming in Movies Mahmoud Azab, Mingzhe Wang, Max Smith, Noriyuki Kojima, Jia Deng, Rada Mihalcea University of Michigan Stacking with Auxiliary Features for Visual Question Answering Nazneen Fatema Rajani and Raymond Mooney The University of Texas at Austin The Emergence of Semantics in Neural Network Representations of Visual Information Dhanush Dharmaretnam and Alona Fyshe University of Victoria Visual Referring Expression Recognition: What Do Systems Actually Learn? Volkan Cirik, Louis-Philippe Morency, Taylor Berg-Kirkpatrick Carnegie Mellon University Visually Guided Spatial Relation Extraction from Text Taher Rahgooy¹, Umar Manzoor¹, Parisa Kordjamshidi² ¹Tulane University, ²Tulane University / Florida Institute for Human and Machine Cognition (IHMC) Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video Captioning Xin Wang, Yuan-Fang Wang, William Yang Wang University of California, Santa Barbara SMILEE: Symmetric Multi-Modal Interactions with Language-Gesture Enabled (AI) Embodiment (DEMO) Sujeong Kim, David Salter, Luke DeLuccia, Kilho Son, Mohamed R. Amer and Amir Tamrakar Generating Image Captions in Arabic using Root-Word Based Recurrent Neural Networks and Deep Neural Networks (SRW) Vasu Jindal
15:30 - 16:00	Afternoon Coffee - Empire Foyer
16:00 - 17:15	Outstanding Papers and Closing Session (sponsored by Amazon) - Empire Ballroom Chair: Joel Tetreault, Grammarly
4:00PM - 4:18PM Deep Contextualized Word Representations Matthew Peters¹, Mark Neumann¹, Mohit Iyyer¹, Matt Gardner¹, Christopher Clark², Kenton Lee², Luke Zettlemoyer² ¹Allen Institute for Artificial Intelligence, ²University of Washington 4:18PM - 4:36PM Learning to Map Context-Dependent Sentences to Executable Formal Queries Alane Suhr¹, Srinivasan Iyer², Yoav Artzi¹ ¹Cornell University, ²University of Washington 4:36PM - 4:54PM Neural Text Generation in Stories Using Entity Representations as Context Elizabeth Clark, Yangfeng Ji, Noah A. Smith University of Washington 4:54PM - 5:12PM Recurrent Neural Networks as Weighted Language Recognizers Yining Chen¹, Sorcha Gilroy², Andreas Maletti³, Jonathan May⁴, Kevin Knight⁴ ¹Dartmouth College, ²University of Edinburgh, ³Universität Leipzig, ⁴University of Southern California / Information Sciences Institute