Publications

2022

• Exploring Neural Models for Query-Focused Summarization
  Jesse Vig*, Alexander R. Fabbri*, Wojciech Kryściński*, Chien-Sheng Wu, Wenhao Liu
  (*equal contribution)
  NAACL 2022 Findings
  [Paper]
• Improving Factual Consistency in Summarization with Compression-Based Post-Editing
  Alexander R Fabbri, Prafulla Kumar Choubey, Jesse Vig, Chien-Sheng Wu, Caiming Xiong
  arXiv e-print
  [Paper]
• Interactive Model Cards: A Human-Centered Approach to Model Documentation
  Anamaria Crisan*, Margaret Drouhard*, Jesse Vig, Nazneen Rajani
  FAccT 2022
  [Paper]
• iSEA: An Interactive Pipeline for Semantic Error Analysis of NLP Models
  Jun Yuan, Jesse Vig, Nazneen Fatema Rajani
  IUI 2022
  [Paper]

2021

• SummVis: Interactive Visual Analysis of Models, Data, and Evaluation for Text Summarization
  Jesse Vig, Wojciech Kryscinski, Karan Goel, Nazneen Fatema Rajani
  ACL System Demonstrations 2021
  [Paper] [Demo Video]
• BERTology Meets Biology: Interpreting Attention in Protein Language Models
  Jesse Vig, Ali Madani, Lav R. Varshney, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani
  ICLR 2021
  [Paper] [Blog] [Demo Video]
• Robustness Gym: Unifying the NLP Evaluation Landscape
  Karan Goel*, Nazneen Rajani*, Jesse Vig, Zachary Taschdjian, Mohit Bansal, Christopher Ré
  NAACL 2021 System Demonstration
  [Paper]
• Robustness Gym: Unifying the NLP Evaluation Landscape
  Karan Goel*, Nazneen Rajani*, Jesse Vig, Samson Tan, Jason Wu, Stephan Zheng, Caiming Xiong, Mohit Bansal, Christopher Ré
  arXiv e-print
  [Paper]
• CaPE: Contrastive Parameter Ensembling for Reducing Hallucination in Abstractive Summarization
  Prafulla Kumar Choubey, Alexander R. Fabbri, Jesse Vig, Chien-Sheng Wu, Wenhao Liu, Nazneen Fatema Rajani
  arXiv e-print
  [Paper]

2020

• Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models
  Pascal Sturmfels, Jesse Vig, Ali Madani, Nazneen Fatema Rajani
  Machine Learning for Structured Biology NeurIPS Workshop 2020
  Learning Meaningful Representations for Life NeurIPS Workshop 2020
  [Paper]
Investigating Gender Bias in Language Models Using Causal Mediation Analysis
Jesse Vig*, Sebastian Gehrmann*, Yonatan Belinkov*, Sharon Qian, Daniel Nevo, Yaron Singer, Stuart Shieber (*equal contribution)
NeurIPS 2020, Spotlight Presentation
[Paper] [Video] [Poster]
• Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias
  Jesse Vig*, Sebastian Gehrmann*, Yonatan Belinkov*, Sharon Qian, Daniel Nevo, Yaron Singer, Stuart Shieber (*equal contribution)
  arXiv e-print
  [Paper]

2019

• Analyzing the Structure of Attention in a Transformer Language Model
  Jesse Vig, Yonatan Belinkov
  ACL BlackboxNLP Workshop 2019
  [Paper] [Poster]
• A Multiscale Visualization of Attention in the Transformer Model
  Jesse Vig
  ACL System Demonstrations 2019
  [Paper] [Poster] [Blog]
• Deconstructing BERT: Visualizing the Inner Workings of Attention
  Jesse Vig
  IEEE Vis Workshop on Visualization for AI Explainability 2019
  [Explainable]

2018

• Comparison of Transfer-Learning Approaches for Response Selection in Multi-Turn Conversations
  Jesse Vig and Kalai Ramea
  DSTC7 Workshop 2018
  [Paper]

2012

• The Tag Genome: Encoding Community Knowledge to Support Novel Interaction
  Jesse Vig, Shilad Sen, John Riedl
  ACM TiiS 2012
  [Paper]

2011

• Navigating the Tag Genome
  Jesse Vig, Shilad Sen, John Riedl
  IUI 2011
  🥇 Best Paper Nomination [Paper]

2010

• Tag Expression: Tagging with Feeling
  Jesse Vig, Matthew Soukup, Shilad Sen, John Riedl
  UIST 2010
  [Paper]

2009

• Tagommenders: Connecting Users to Items through Tags
  Shilad Sen, Jesse Vig, John Riedl
  WWW 2009
  [Paper]
• Tagsplanations: Explaining Recommendations Using Tags
  Jesse Vig, Shilad Sen, John Riedl
  IUI 2009
  🥇 Best Paper [Paper]
• Learning to Recognize Valuable Tags
  Shilad Sen, Jesse Vig, John Riedl
  IUI 2009
  [Paper]