#1 Importance of the Single-Span Task Formulation to Extractive Question-Answering [abstract] [poster] [video]
Marie-Anne Xu, Rahul Khanna
#2 Simulated Multiple Reference Training Improves Low-Resource Machine Translation [paper] [poster] [video]
Huda Khayrallah, Brian Thompson, Matt Post, Philipp Koehn
#3 Contextual Datetime Language Model Adaptation for Speech Recognition [abstract] [poster] [video]
Richard Diehl Martinez, Scott Novotney, Ivan Bulyko, Andreas Stolcke
#4 Large-scale Resource-efficient Models for Task-oriented Dialog with Augmentation and Distillation [abstract] [poster] [video]
Haoda Chu, Subhabrata Mukherjee, Minwoo Jeong, Ahmed Awadallah, Ming Wu
#6 Bias Aware Training [abstract] [poster] [video]
Huiting Liu, Peter Grasch, Sachin Agarwal
#7 Generating Natural Questions from Images for Multimodal Assistant [abstract] [poster] [video]
Alkeshkumar Patel, Akanksha Bindal, Hadas Kotak, Christopher Klein, Jason Williams
#8 NLPStatTest: A Toolkit for Comparing NLP System Performance [abstract] [poster] [video]
Haotian Zhu, Denise Mak, Jesse Gioannini, Fei Xia
#10 Multilingual Punctuation restoration using joint modeling transformer technique [abstract] [poster] [video]
Varnith Chordia
#11 Streaming Models for Joint Speech Recognition and Translation [abstract] [poster] [video]
Orion Weller, Matthias Sperber, Christian Gollan, Joris Kluivers
#12 Consistent Transcription and Translation of Speech [paper] [poster] [video]
Matthias Sperber, Hendra Setiawan, Christian Gollan, Udhyakumar Nallasamy, Matthias Paulik
#13 Student Forcing Knowledge Distillation [abstract] [poster] [video]
Yi-Hsiu Liao, Udhyakumar Nallasamy
#14 Small Data FAQ Retrieval [abstract] [poster] [video]
Kathleen Preddy, Michael Baxter
#15 Unsupervised Multilingual Alignment using Wasserstein Barycenter [paper] [poster] [video]
Xin Lian, Kshitij Jain, Jakub Truszkowski, Pascal Poupart, Yaoliang Yu
#16 Sparse Optimization for Unsupervised Extractive Summarization of Long Documents with the Frank-Wolfe Algorithm [abstract] [poster] [video]
Alicia Tsai, Laurent El Ghaoui
#17 Improving Slot Filling Reliability in a Commercial Spoken Personal Assistant [abstract] [poster] [video]
Eric Gu, Jean-Philippe Fauconnier, Deepanshu Gupta, Siddharth Patwardhan
#18 Improved Word Alignments via Shifted Alignment Training [abstract] [poster] [video]
Sarthak Garg, Stephan Peitz, Yi-Hsiu Liao, Ilya Chatsviorkin, Udhyakumar Nallasamy
#19 Semantic Complexity in End-to-End Spoken Language Understanding [paper] [poster] [video]
Samridhi Choudhary
#20 Multi-Variant Arabic Language Model for Keyboard Input [abstract] [poster] [video]
Hala Almaghout, Jerome Bellegarda, Brent Ramerth, Giulia Pagallo
#22 Revisiting Evaluation of Knowledge Base Completion Models [paper] [poster] [video]
Pouya Pezeshkpour, Yifan Tian, Sameer Singh
#23 Constraint-Based Data Collection for Evaluating Model Robustness [abstract] [poster] [video]
Stefan Larson, Anthony Zheng, Anish Mahendran, Rishi Tekriwal, Adrian Cheung, Eric Guldan, Kevin Leach, Jonathan Kummerfeld
#24 Let's Go Camping: Development of a Novel Corpus of Negotiation Dialogues for Building Automatically Negotiating Agents [abstract] [poster] [video]
Kushal Chawla, Jaysa Ramirez, Rene Clever, Gale Lucas, Jonathan Gratch
#25 Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders [paper] [poster] [video]
Terra Blevins, Luke Zettlemoyer
#26 ETC: Encoding Long and Structured Inputs in Transformers [paper] [poster] [video]
Joshua Ainslie, Santiago Ontanon, Chris Alberti, Vaclav Cvicek, Zach Fisher, Philip Pham, Anirudh Ravula, Sumit Sanghai, Qifan Wang, Li Yang
#27 On the Evaluation of Machine Translation n-best Lists [paper] [poster] [video]
Jacob Bremerman, Huda Khayrallah, Douglas Oard, Matt Post
#28 They, Them, Theirs: Rewriting with Gender-neutral English [abstract] [poster] [video]
Tony Sun, Kellie Webster, William Yang Wang, Melvin Johnson
#29 AUTOPROMPT: Eliciting Knowledge from Language Models with Automatically Generated Prompts [abstract] [poster] [video]
Taylor Shin, Yasaman Razeghi, Robert Logan, Eric Wallace, Sameer Singh
#31 Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker [abstract] [poster] [video]
Amol Kelkar, Rohan Relan, Vaishali Bhardwaj, Saurabh Vaichal, Peter Relan
#33 Entity Resolution by Clustering Contextualized Mention Embeddings [abstract] [poster] [video]
Robert Logan, Daniel Bikel
#34 Are Some Words Worth More than Others? [abstract] [poster] [video]
Shiran Dudy, Steven Bedrick
#35 Automatic Extraction of Syntagmatic Relations for Word Sense Disambiguation [abstract] [poster] [video]
Alex Dodge
#36 Multilingual Named Entity Recognition in Tweets using Wikidata [abstract] [poster] [video]
Ramy Eskander, Peter Martigny, Shubhanshu Mishra
#37 LDA in the Wild: How Practitioners Develop Topic Models [abstract] [poster] [video]
Theo Bayard de Volo, Alfredo Gomez, Tatsuki Kuze, Alexandra Schofield
#38 Semantic Approach to Agent Routing Using a Hybrid Attribute-based Recommender System [abstract] [poster] [video]
Anwitha Paruchuri, Anshuma Chandak
#39 Self-Training for End-to-End Speech Translation [paper] [poster] [video]
Juan Pino, Qiantong Xu, Xutai Ma, Javad Dousti, Yun Tang
#40 Iterative Graph Traversal and Ranking for Question Answering [abstract] [poster] [video]
Madhulima Pandey, Zhen Tan, Manasi Joglekar, Manish Pandey
#41 Two Three-stage Methods for Extreme Multi-label Classification [abstract] [poster] [video]
Yao Xuan, Anna Sun, Xing Zhou, Aashu Singh, Justin Zhang, Annie Liu
#42 Hierarchical Multi-label Classification using label embedding [abstract] [poster] [video]
Aashu Bishvnath Singh, Qiaoying Huang, Annie Liu
#43 RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models [paper] [poster] [video]
Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, Noah A. Smith
#44 Representing Numbers in Language Models [abstract] [poster] [video]
Avijit Thawani, Jay Pujara, Filip Ilievski, Pedro Szekely
#46 MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics [abstract] [poster] [video]
Anthony Chen, Gabriel Stanovsky, Sameer Singh, Matt Gardner
#47 Best Practices for Data-Efficient Modeling in NLG: How to Train Production-Ready Neural Models with Less Data [paper] [poster] [video]
Ankit Arun, Soumya Batra, Vikas Bhardwaj, Ashwini Challa, Pinar Donmez, Peyman Heidari, Hakan Inan, Shashank Jain, Anuj Kumar, Shawn Mei, Karthik Mohan, Michael White
#48 Gradient-based Analysis of NLP Models is Manipulable [paper] [poster] [video]
Junlin Wang, Jens Tuyls, Eric Wallace, Sameer Singh
#49 InDiE: Generation of complex database queries and API calls from natural language utterances [abstract] [poster] [video]
Amol Kelkar, Nachiketa Rajpurohit, Utkarsh Mittal, Peter Relan
#50 Improving Social Media Information Extraction using Multitask Multidataset Learning [abstract] [poster] [video]
Shubhanshu Mishra
#51 Finding Newness: Leveraging Memory Networks to Detect Document Novelty [abstract] [poster] [video]
Tirthankar Ghosal, Vignesh Edithal, Asif Ekbal
#52 Leveraging Multi-Premise Inference for Document-Level Novelty Detection [abstract] [poster] [video]
Tirthankar Ghosal, Tameesh Biswas, Asif Ekbal
#53 Tweeki: Linking Named Entities on Twitter to a Knowledge Graph [abstract] [poster] [video]
Bahareh Harandizadeh, Sameer Singh
#56 Neural Databases [abstract] [poster] [video]
James Thorne, Majid Yazdani, Marzieh Saeidi, Sebastian Riedel, Alon Halevy
#57 PHOTON: A Robust Cross-Domain Text-to-SQL System [paper] [poster] [video]
Victoria Lin, Jichuan Zeng, Caiming Xiong, Richard Socher, Steven Hoi
#58 Democratizing Conversational AI: A Human-Machine Collaborative Approach to Mixed-Initiative AI Chatbots [abstract] [poster] [video]
Michelle Zhou, Huahai Yang, Wenxi Chen, Vi Tu
#60 Social Bias Frames: Reasoning about Social and Power Implications of Language [paper] [poster] [video]
Maarten Sap, Saadia Gabriel, Lianhui Qin, Dan Jurafsky, Noah Smith, Yejin Choi
#61 Self-Training for Compositional Neural NLG [abstract] [poster] [video]
Xintong Li, Michael White
#62 Understanding Psycho-Linguistic Dimensions of Phishing Using Large-Scale Language Models [abstract] [poster] [video]
Kayla Duskin, Svitlana Volkova
#63 Generative Models for Understanding Linguistic and Stylistic Properties of Deception [abstract] [poster] [video]
Emily Saldanha, Svitlana Volkova
#65 Evaluating the Robustness of Neural Deception Detection Models against Linguistic Adversarial Attacks [abstract] [poster] [video]
Maria Glenski, Ellyn Ayton, Robin Cosbey, Dustin Arendt, Svitlana Volkova
#66 Analyzing the Robustness of Neural Linguistic Deception Detection across Domains, Modalities, and Languages [abstract] [poster] [video]
Ellyn Ayton, Robin Cosbey, Dustin Arendt, Svitlana Volkova, Maria Glenski