June 6, 2021 - June 11, 2021

Microsoft at NAACL 2021

Lieu: Virtual

Toutes les heures sont en PDT (UTC -7)

09:00 – 09:50 Talk session

When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messages
Publications connexes
- When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messages
  
  Stojan Trajanovski, Chad Atalla, Kunho Kim, Vipul Agarwal, Milad Shokouhi, Chris Quirk
10:20 – 11:10 Talk session

APo-VAE: Text Generation in Hyperbolic Space
Publications connexes
- APo-VAE: Text Generation in Hyperbolic Space
  
  Shuyang Dai, Zhe Gan, Yu Cheng, Chenyang Tao, JJ (Jingjing) Liu
10:20 – 11:10 Talk session

MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Publications connexes
- MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
  
  Mengzhou Xia, Guoqing Zheng, Subhabrata (Subho) Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Awadallah
10:20 – 11:10 Talk session

Summarization
Publications connexes
- Noisy Self-Knowledge Distillation for Text Summarization
  
  Yang Liu, Sheng Shen, Mirella Lapata
- Enhancing Factual Consistency of Abstractive Summarization
  
  Chenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang, Meng Jiang
11:40 – 12:30 Talk session

Self-Training with Weak Supervision
Publications connexes
- Self-training with Weak Supervision
  
  Giannis Karamanolakis, Subhabrata (Subho) Mukherjee, Guoqing Zheng, Ahmed Awadallah
11:40 – 12:30 Talk session

3D: Language Grounding to Vision, Robotics and Beyond
Publications connexes
- LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval
  
  Siqi Sun, Yen-Chun Chen, Linjie Li, Shuohang Wang, Yuwei Fang, JJ (Jingjing) Liu
- Modular Networks for Compositional Instruction Following
  
  Rodolfo Corona, Daniel Fried, Coline Devin, Dan Klein, Trevor Darrell
11:40 – 12:30 Talk session

Posterior Differential Regularization with f-divergence for Improving Model Robustness
Publications connexes
- Posterior Differential Regularization with f-divergence for Improving Model Robustness
  
  Hao Cheng, Xiaodong Liu, Lis Pereira, Yaoliang Yu, Jianfeng Gao
17:00 – 17:50 Talk session

The Curious Case of Hallucinations in Neural Machine Translation
Publications connexes
- The Curious Case of Hallucinations in Neural Machine Translation
  
  Vikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt
17:00 – 17:50 Talk session

4C: Sentence-level Semantics and Textual Inference
Publications connexes
- Understanding by Understanding Not: Modeling Negation in Language Models
  
  Arian Hosseini, Siva Reddy, Dzmitry Bahdanau, Devon Hjelm, Alessandro Sordoni, Aaron Courville
- Structure-Grounded Pretraining for Text-to-SQL
  
  Xiang Deng, Ahmed Awadallah, Chris Meek, Alex Polozov, Huan Sun, Matthew Richardson
18:20 – 19:10 Talk session

Machine Learning for NLP: Language Modeling and Sequence to Sequence Models
Publications connexes
- Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic Oracle
  
  Yikang Shen, Shawn Tan, Alessandro Sordoni, Siva Reddy, Aaron Courville
- Mask Attention Networks: Rethinking and Strengthen Transformer
  
  Zhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao, Nan Duan, Ruofei Zhang, Xuanjing Huang
- ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding
  
  Dongling Xiao, Yu-Kun Li, Han Zhang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
18:20 – 19:10 Talk session

Modeling Event Plausibility with Consistent Conceptual Abstraction
Publications connexes
- Modeling Event Plausibility with Consistent Conceptual Abstraction
  
  Ian Porada, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
19:40 – 20:30 Talk session

Speech
Publications connexes
- SPLAT: Speech-Language Joint Pre-Training for Spoken Language Understanding
  
  Yu-An Chung, Chenguang Zhu, Michael Zeng
- Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks
  
  Siddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze, Shinji Watanabe
19:40 – 20:30 Talk session

DA-Transformer: Distance-aware Transformer
Publications connexes
- DA-Transformer: Distance-aware Transformer
  
  Chuhan Wu, Fangzhao Wu, Yongfeng Huang
19:40 – 20:30 Talk session

Language Resources and Evaluation
Publications connexes
- Are NLP Models Really Able to Solve Simple Math Word Problems?
  
  Arkil Patel, Satwik Bhattamishra, Navin Goyal
- Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge
  
  Canwen Xu, Wangchunshu Zhou, Tao Ge, Ke Xu, Julian J. McAuley, Furu Wei
19:40 – 20:30 Talk session

Language Scaling for Universal Suggested Replies Model
Publications connexes
- Language Scaling for Universal Suggested Replies Model
  
  Qianlan Ying, Payal Bajaj, Budhaditya Deb, Yu Yang, Wei Wang, Bojia Lin, Milad Shokouhi, Xia Song, Yang Yang, Daxin Jiang (姜大昕)

09:00 – 09:50 Talk session

Detoxifying Language Models Risks Marginalizing Minority Voices
Publications connexes
- Detoxifying Language Models Risks Marginalizing Minority Voices
  
  Albert Xu, Eshaan Pathak, Eric Wallace, Suchin Gururangan, Maarten Sap, Dan Klein
09:00 – 09:50 Talk session

From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding
Publications connexes
- From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding
  
  Rob van der Goot, Ibrahim Sharaf, Aizhan Imankulova, Ahmet Üstün, Marija Stepanović, Alan Ramponi, Siti Oryza Khairunnisa, Mamoru Komachi, Barbara Plank
10:20 – 11:10 Talk session

Learning to Decompose and Organize Complex Tasks
Publications connexes
- Learning to Decompose and Organize Complex Tasks
  
  Yi Zhang, Sujay Kumar Jauhar, Julia Kiseleva, Ryen W. White, Dan Roth
10:20 – 11:10 Talk session

Sentence-level Semantics and Textual Inference
Publications connexes
- FLIN: A Flexible Natural Language Interface for Web Navigation
  
  Sahisnu Mazumder, Oriana Riva
- Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention
  
  Pengcheng Yin, Hao Fang, Graham Neubig, Adam Pauls, Emmanouil Antonios Platanios, Yu Su, Sam Thomson, Jacob Andreas
17:00 – 17:50 Talk session

Reading and Acting While Blindfolded: The Need for Semantics in Text Game Agents
Publications connexes
- Reading and Acting While Blindfolded: The Need for Semantics in Text Game Agents
  
  Shunyu Yao, Karthik Narasimhan, Matthew Hausknecht
18:20 – 19:10 Talk session

FUDGE: Controlled Text Generation with Future Discriminators
Publications connexes
- FUDGE: Controlled Text Generation with Future Discriminators
  
  Kevin Yang, Dan Klein
18:20 – 19:10 Talk session

InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training
Publications connexes
- InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training
  
  Zewen Chi, Li Dong, Furu Wei, Nan Yang, Saksham Singhal, Wenhui Wang, Xia Song, Xian-Ling Mao, Heyan Huang, Ming Zhou
19:40 – 21:00 Talk session

Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels
Publications connexes
- Privacy Regularization: Joint Privacy-Utility Optimization in Language Models
  
  Fatemehsadat Mireshghallah, Huseyin Inan, Marcello Hasegawa, Victor Rühle, Taylor Berg-Kirkpatrick, Robert Sim
19:40 – 20:30 Talk session

UniDrop: A Simple Yet Effective Technique to Improve Transformer without Extra Cost
Publications connexes
- UniDrop: A Simple Yet Effective Technique to Improve Transformer without Extra Cost
  
  Zhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie, Tao Qin, Xinyu Dai, Tie-Yan Liu
19:40 – 21:00 Talk session

Smart-Start Decoding for Neural Machine Translation
Publications connexes
- Smart-Start Decoding for Neural Machine Translation
  
  Jian Yang, Shuming Ma, Dongdong Zhang, Juncheng Wan, Zhoujun Li, Ming Zhou

09:00 – 10:20 Talk session

Ask what’s missing and what’s useful: Improving Clarification Question Generation using Global Knowledge
Publications connexes
- Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge
  
  Bodhisattwa Prasad Majumder, Sudha Rao, Michel Galley, Julian J. McAuley
10:20 – 11:10 Talk session

Extracting a Knowledge Base of Mechanisms from COVID-19 Papers
Publications connexes
- Extracting a Knowledge Base of Mechanisms from COVID-19 Papers
  
  Tom Hope, Aida Amini, David Wadden, Madeleine van Zuylen, Sravanthi Parasa, Eric Horvitz, Daniel Weld, Roy Schwartz, Hannaneh Hajishirzi
10:20 – 11:10 Talk session

Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
Publications connexes
- Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
  
  Chen Zhao, Chenyan Xiong, Jordan L. Boyd-Graber, Hal Daumé III
10:20 – 11:10 Talk session

Constructing Taxonomies from Pretrained Language Models
Publications connexes
- Constructing Taxonomies from Pretrained Language Models
  
  Catherine Chen, Kevin Lin, Dan Klein
10:20 – 11:10 Talk session

Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
Publications connexes
- Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization
  
  Yichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao
17:50 – 18:20 Talk session

An Empirical Study on Neural Keyphrase Generation
Publications connexes
- An Empirical Study on Neural Keyphrase Generation
  
  Rui Meng, Xingdi Yuan, Tong Wang, Sanqiang Zhao, Adam Trischler, Daqing He
17:50 – 18:20 Talk session

Contextualized Perturbation for Textual Adversarial Attack
17:50 – 18:20 Talk session

Text Editing by Command
Publications connexes
- Text Editing by Command
  
  Felix Faltings, Michel Galley, Gerold Hintz, Chris Brockett, Chris Quirk, Jianfeng Gao, Bill Dolan
18:20 – 19:10 Talk session

Machine Learning for NLP: Classification and Structured Prediction Models
Publications connexes
- BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text Classification
  
  Ishani Mondal
- Targeted Adversarial Training for Natural Language Understanding
  
  Lis Pereira, Xiaodong Liu, Hao Cheng, Hoifung Poon, Jianfeng Gao, Ichiro Kobayashi
18:20 – 19:10 Talk session

NLP Applications
Publications connexes
- TITA: A Two-stage Interaction and Topic-Aware Text Matching Model
  
  Xingwu Sun, Yanling Cui, Hongyin Tang, Qiuyu Zhu, Fuzheng Zhang, Beihong Jin
- Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
  
  Jason Wei, Chengyu Huang, Soroush Vosoughi, Yu Cheng, Shiqi Xu
18:20 – 19:10 Talk session

GPT Perdetry Test: Generating new meanings for new words
Publications connexes
- GPT Perdetry Test: Generating new meanings for new words
  
  Nikolay Malkin, Sameera Lanka, Pranav Goel, Sudha Rao, Nebojsa Jojic
18:20 – 19:10 Talk session

NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction
Publications connexes
- NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction
  
  Ahmed Elgohary, Chris Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, Ahmed Awadallah
19:40 – 20:30 Talk session

Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph
Publications connexes
- Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph
  
  Yucheng Zhou, Xiubo Geng, Tao Shen, Wenqiang Zhang, Daxin Jiang (姜大昕)
20:30 – 21:00 Talk session

16E: Summarization
Publications connexes
- QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
  
  Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir R. Radev
- MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization
  
  Chenguang Zhu, Yang Liu, Jie Mei, Michael Zeng

08:00 – 16:00 Workshop

Second Workshop on Scholarly Document Processing (SDP 2021)

Organizer: Kuansan Wang
08:00 – 09:00 Workshop

Ninth International Workshop on Natural Language Processing for Social Media (SocialNLP 2021)

Program Committee Members: Monojit Choudhury, Lei Cui, Ming Zhou
08:00 – 16:00 Workshop

Teaching NLP

Program Committee Member: Su Lin Blodgett

Workshop Day 1: June 10

08:00 – 16:00 Workshop

Fifth Workshop on Computational Approaches to Linguistic Code Switching

Program Committee Members: Kalika Bali, Monojit Choudhury

Organizers: Sunayana Sitaram, Anirudh Srinivasan
08:00 – 16:00 Workshop

Teaching NLP

Program Committee Member: Su Lin Blodgett

Workshop Day 2: June 11
08:00 – 16:00 Workshop

2nd Workshop on Advances in Language and Vision Research (ALVR 2021)

Program Committee Members: Zhe Gan, Hamid Palangi
08:00 – 16:00 Workshop

The Third Workshop on Narrative Understanding

Program Committee Member: Somnath Basu, Roy Chowdhury

Microsoft at NAACL 2021

Monday, June 7, 2021

When does text prediction benefit from additional context? An exploration of contextual signals for chat and email messages

APo-VAE: Text Generation in Hyperbolic Space

MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning

Summarization

Self-Training with Weak Supervision

3D: Language Grounding to Vision, Robotics and Beyond

Posterior Differential Regularization with f-divergence for Improving Model Robustness

The Curious Case of Hallucinations in Neural Machine Translation

4C: Sentence-level Semantics and Textual Inference

Machine Learning for NLP: Language Modeling and Sequence to Sequence Models

Modeling Event Plausibility with Consistent Conceptual Abstraction

Speech

DA-Transformer: Distance-aware Transformer

Language Resources and Evaluation

Language Scaling for Universal Suggested Replies Model

Tuesday, June 8, 2021

Detoxifying Language Models Risks Marginalizing Minority Voices

From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding

Learning to Decompose and Organize Complex Tasks

Sentence-level Semantics and Textual Inference

Reading and Acting While Blindfolded: The Need for Semantics in Text Game Agents

FUDGE: Controlled Text Generation with Future Discriminators

InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training

Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModels

UniDrop: A Simple Yet Effective Technique to Improve Transformer without Extra Cost

Smart-Start Decoding for Neural Machine Translation

Wednesday, June 9, 2021

Ask what’s missing and what’s useful: Improving Clarification Question Generation using Global Knowledge

Extracting a Knowledge Base of Mechanisms from COVID-19 Papers

Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval

Constructing Taxonomies from Pretrained Language Models

Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization

An Empirical Study on Neural Keyphrase Generation

Contextualized Perturbation for Textual Adversarial Attack

Text Editing by Command

Machine Learning for NLP: Classification and Structured Prediction Models

NLP Applications

GPT Perdetry Test: Generating new meanings for new words

NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction

Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph

16E: Summarization

Thursday, June 10, 2021

Second Workshop on Scholarly Document Processing (SDP 2021)

Ninth International Workshop on Natural Language Processing for Social Media (SocialNLP 2021)

Teaching NLP

Friday, June 11, 2021

Fifth Workshop on Computational Approaches to Linguistic Code Switching

Teaching NLP

2nd Workshop on Advances in Language and Vision Research (ALVR 2021)

The Third Workshop on Narrative Understanding