WeCNLP
Posters and Sponsors
Apple
Join us. Be you.
Amazon
Join us! Serve millions of customers worldwide through cutting edge AI Research!
Facebook Inc
Importance of the Single-Span Task Formulation to Extractive Question-Answering
Marie-Anne Xu (Crystal Springs Uplands School)*; Rahul Khanna (University of Southern California)
Contextual Datetime Language Model Adaptation for Speech Recognition
Richard Diehl Martinez (Amazon)*; Scott Novotney (Amazon); Ivan Bulyko (Amazon); Andreas Stolcke (Amazon)
Bias Aware Training
Huiting Liu (Apple Inc.)*; Peter Grasch (Apple Inc.); Sachin Agarwal (Apple)
NLPStatTest: A Toolkit for Comparing NLP System Performance
Haotian Zhu (University of Washington)*; Denise P Mak (University of Washington ); Jesse A Gioannini (University of Washington); Fei Xia (University of Washington)
Streaming Models for Joint Speech Recognition and Translation
Orion Weller (Apple)*; Matthias Sperber (Apple); Christian Gollan (Apple); Joris Kluivers (Apple)
Consistent Transcription and Translation of Speech
Matthias Sperber (Apple)*; Hendra Setiawan (Apple); Christian Gollan (Apple); Udhyakumar Nallasamy (Apple); Matthias Paulik (Apple)
Unsupervised Multilingual Alignment using Wasserstein Barycenter
Xin Lian (University of Waterloo); Kshitij Jain (Amazon)*; Jakub Truszkowski (Borealis AI); Pascal Poupart (University of Waterloo); Yaoliang Yu (University of Waterloo)
Improving Slot Filling Reliability in a Commercial Spoken Personal Assistant
Eric Gu (Apple Inc. ); Deepanshu Gupta (Apple Inc. ); Jean-Philippe Fauconnier (Apple Inc. )*; Sid Patwardhan (Apple Inc. )
Improved Word Alignments via Shifted Alignment Training
Sarthak Garg (Apple Inc.)*; Stephan Peitz (Apple Inc.); Yi-Hsiu Liao (Apple); Ilya Chatsviorkin (Apple Inc.); Udhyakumar Nallasamy (Apple)
Revisiting Evaluation of Knowledge Base Completion Models
Pouya Pezeshkpour (UCI)*; Yifan Tian (UCI); Sameer Singh (University of California, Irvine)
Let's Go Camping: Development of a Novel Corpus of Negotiation Dialogues for Building Automatically Negotiating Agents
Kushal Chawla (University of Southern California)*; Jaysa Ramirez (Rollins College); Rene Clever (CUNY Lehman College); Gale Lucas (University of Southern California); Jonathan Gratch (Institute for Creative Technologies)
ETC: Encoding Long and Structured Inputs in Transformers
Joshua T Ainslie (Google LLC)*; Santiago Ontanon (Google LLC); Chris Alberti (Google); Vaclav Cvicek (Google LLC); Zach Fisher (Google LLC); Philip M Pham (Google Research); Anirudh Ravula (Google); Sumit Sanghai (Google LLC); Qifan Wang (Google Research); Li Yang (Google Research)
AUTOPROMPT: Eliciting Knowledge from Language Models with Automatically Generated Prompts
Taylor Shin (University of California Irvine); Yasaman Razeghi (University of California Irvine)*; Robert L Logan (UC Irvine); Eric Wallace (U.C. Berkeley); Sameer Singh (University of California, Irvine)
Entity Resolution by Clustering Contextualized Mention Embeddings
Robert L Logan (UC Irvine)*; Daniel Bikel (Google Research)
Automatic Extraction of Syntagmatic Relations for Word Sense Disambiguation
Alex Dodge (SDSU)*
LDA in the Wild: How Practitioners Develop Topic Models
Theo Bayard de Volo (Pitzer College); Alfredo Gomez (Harvey Mudd College); Tatsuki Kuze (Harvey Mudd College); Alexandra K Schofield (Harvey Mudd College)*
Self-Training for End-to-End Speech Translation
Juan Miguel Pino (Facebook)*; Qiantong Xu (Facebook AI Research); Xutai Ma (Johns Hopkins University); Javad Dousti (Facebook); Yun Tang (Facebook)
Two Three-stage Methods for Extreme Multi-label Classification
Yao Xuan (University of California, Santa Barbara/Facebook)*; Anna Sun (Facebook); Xing Zhou (Facebook); Aashu Singh (Facebook); Justin Zhang (Facebook); Annie Liu (Facebook)
Hierarchical Multi-label Classification using label embedding
Aashu Bishvnath Singh (Facebook)*; Qiaoying Huang (Rutgers University); Annie Liu (Facebook)
MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics
Anthony Chen (University of California, Irvine)*; Gabriel Stanovsky (Allen Institute for AI); Sameer Singh (University of California, Irvine); Matt Gardner (AI2)
Gradient-based Analysis of NLP Models is Manipulable
Junlin Wang (UCI)*; Jens Tuyls (UC Irvine); Sameer Singh (University of California, Irvine); Eric Wallace (U.C. Berkeley)
Finding Newness: Leveraging Memory Networks to Detect Document Novelty
Tirthankar Ghosal (IIT Patna)*; Vignesh Edithal (IIT Patna); Asif Ekbal (IIT Patna)
Leveraging Multi-Premise Inference for Document-Level Novelty Detection
Tirthankar Ghosal (IIT Patna)*; Tameesh Biswas (IIT Patna); Asif Ekbal (IIT Patna)
Tweeki: Linking Named Entities on Twitter to a Knowledge Graph
Bahareh Harandizadeh (University of California, Irvine)*; Sameer Singh (University of California, Irvine)
Understanding Psycho-Linguistic Dimensions of Phishing Using Large-Scale Language Models
Kayla Duskin (PNNL)*; Svitlana Volkova (Pacific Northwest National Laboratory)
Generative Models for Understanding Linguistic and Stylistic Properties of Deception
Emily G Saldanha (Pacific Northwest National Laboratory)*; Svitlana Volkova (Pacific Northwest National Laboratory)
Evaluating the Robustness of Neural Deception Detection Models against Linguistic Adversarial Attacks
Maria Glenski (Pacific Northwest National Laboratory)*; Ellyn Ayton (Pacific Northwest National Laboratory); Robin Cosbey (Pacific Northwest National Laboratory); Dustin Arendt (Pacific Northwest National Laboratory); Svitlana Volkova (Pacific Northwest National Laboratory)
Analyzing the Robustness of Neural Linguistic Deception Detection across Domains, Modalities, and Languages
Ellyn M Ayton (Pacific Northwest National Laboratory)*; Robin Cosbey (Western Washington University); Dustin Arendt (Pacific Northwest National Laboratory); Svitlana Volkova (Pacific Northwest National Laboratory); Maria Glenski (Pacific Northwest National Laboratory)
They, Them, Theirs: Rewriting with Gender-neutral English
Tony Sun (UC Santa Barbara)*; Kellie Webster (Google); William Yang Wang (UC Santa Barbara); Melvin Johnson (Google)
Large-scale Resource-efficient Models for Task-oriented Dialog with Augmentation and Distillation
Haoda Chu (Microsoft)*; Subhabrata Mukherjee (Microsoft Research); Minwoo Jeong (Microsoft); Ahmed Awadallah (Microsoft); Ming Wu (Microsoft)
Generating Natural Questions from Images for Multimodal Assistant
Alkeshkumar M Patel (Apple Inc.)*; Akanksha Bindal (Apple Inc.); Hadas Kotak (Apple Inc.); Christopher Klein (Apple Inc.); Jason Williams (Apple)
Multilingual Punctuation restoration using joint modeling transformer technique
Varnith Chordia (Palo Alto Research Center)*
Student Forcing Knowledge Distillation
Yi-Hsiu Liao (Apple)*; Udhyakumar Nallasamy (Apple)
Small Data FAQ Retrieval
Kathleen A Preddy (AllyO)*; Michael Baxter (AllyO)
Sparse Optimization for Unsupervised Extractive Summarization of Long Documents with the Frank-Wolfe Algorithm
Alicia Y. Tsai (University of California, Berkeley)*; Laurent El Ghaoui (UC Berkeley)
Semantic Complexity in End-to-End Spoken Language Understanding
Samridhi S Choudhary (Amazon)*
Multi-Variant Arabic Language Model for Keyboard Input
Hala Almaghout (Apple)*; Jerome Bellegarda (Apple Inc.); BRENT RAMERTH (APPLE); Giulia Pagallo (Apple)
Constraint-Based Data Collection for Evaluating Model Robustness
Stefan Larson (unaffiliated)*; Anthony Zheng (University of Michigan); Anish Mahendran (University of Michigan); Rishi Tekriwal (University of Michigan); Adrian Cheung (Clinc, Inc.); Eric Guldan (University of Michigan); Kevin Leach (University of Michigan); Jonathan K Kummerfeld (University of Michigan)
Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders
Terra Blevins (University of Washington; Facebook AI)*; Luke Zettlemoyer (University of Washington)
On the Evaluation of Machine Translation n-best Lists
Jacob Bremerman (University of Maryland)*; Huda Khayrallah (Johns Hopkins University); Douglas Oard (University of Maryland); Matt Post (Johns Hopkins University)
Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker
Amol Kelkar (Got It, Inc)*; Rohan Relan (Got It, Inc); Vaishali Bhardwaj (Got It, Inc); Saurabh Vaichal (Got It, Inc); Peter Relan (Got It, Inc)
Are Some Words Worth More than Others?
Shiran Dudy (OHSU)*; Steven Bedrick (OHSU)
Multilingual Named Entity Recognition in Tweets using Wikidata
Ramy Eskander (Columbia University); Peter Martigny (Twitter); SHUBHANSHU MISHRA (Twitter Inc.)*
SEMANTIC APPROACH TO AGENT ROUTING USING A HYBRID ATTRIBUTE-BASED RECOMMENDER SYSTEM
Anwitha Paruchuri (Accenture)*; Anshuma Chandak (Accenture)
Iterative Graph Traversal and Ranking for Question Answering
Madhulima Pandey (Sparrow Labs, Stanford University)*; Zhen Tan (Carnegie Mellon University); Manasi Joglekar (Carnegie Mellon University); Manish Pandey (Carnegie Mellon University)
RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Samuel I Gehman (University of Washington)*; Suchin Gururangan (Allen Institute for Artificial Intelligence); Maarten Sap (University of Washington); Yejin Choi (University of Washington); Noah A Smith (University of Washington and Allen Institute for AI)
Representing Numbers in Language Models
Avijit Thawani (University of Southern California)*; Jay Pujara (University of Southern California); Pedro Szekely (USC/ISI)
Best Practices for Data-Efficient Modeling in NLG: How to Train Production-Ready Neural Models with Less Data
Ankit Arun (Facebook); Soumya Batra (Facebook); Vikas Bhardwaj (Facebook); Ashwini Challa (Facebook); Pinar Donmez (Facebook); Peyman Heidari (Facebook)*; Hakan Inan (Facebook); Shashank Jain (Facebook); Anuj Kumar (Facebook Conversational AI); Shawn Mei (Facebook); Karthik Mohan (Facebook); Michael White (Ohio State University)
InDiE: Generation of complex database queries and API calls from natural language utterances
Amol Kelkar (Got It, Inc)*; Nachiketa Rajpurohit (Got It, Inc); Utkarsh Mittal (Got It, Inc); Peter Relan (Got It, Inc)
Improving Social Media Information Extraction using Multitask Multidataset Learning
SHUBHANSHU MISHRA (Twitter Inc.)*
Neural Databases
James Thorne (University of Cambridge)*; Majid Yazdani (Facebook); Marzieh Saeidi (Facebook); Sebastian Riedel (); Alon Y Halevy (Facebook)
PHOTON: A Robust Cross-Domain Text-to-SQL System
Victoria Lin (Salesforce)*; Jichuan Zeng (The Chinese University of Hong Kong); Caiming Xiong (Salesforce Research); Richard Socher (Salesforce); Steven Hoi (Salesforce)
Democratizing Conversational AI: A Human-Machine Collaborative Approach to Mixed-Initiative AI Chatbots
Michelle X Zhou (Juji)*; Huahai Yang (Juji, Inc.); Wenxi Chen (Juji, Inc.); Vi Tu (Juji, Inc.)
Self-Training for Compositional Neural NLG
Xintong Li (The Ohio State University)*; Michael White (Ohio State University)
Simulated Multiple Reference Training Improves Low-Resource Machine Translation
Huda Khayrallah (Johns Hopkins University)*; Brian Thompson (Johns Hopkins University); Matt Post (Johns Hopkins University); Philipp Koehn (Johns Hopkins University)
Social Bias Frames: Reasoning about Social and Power Implications of Language
Maarten Sap (University of Washington)*; Saadia Gabriel (University of Washington); Lianhui Qin (University of Washington); Dan Jurafsky (Stanford University); Noah A Smith (University of Washington and Allen Institute for AI); Yejin Choi (University of Washington)