Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Mohit Bansal

Do Language Models Have Beliefs? Methods for Detecting, Updating, and Visualizing Model Beliefs


Nov 26, 2021
Peter Hase, Mona Diab, Asli Celikyilmaz, Xian Li, Zornitsa Kozareva, Veselin Stoyanov, Mohit Bansal, Srinivasan Iyer

* 19 pages 

  Access Paper or Ask Questions

Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions


Nov 01, 2021
Prateek Yadav, Peter Hase, Mohit Bansal

* 26 pages, 6 figures, 8 tables, 5 algorithms 

  Access Paper or Ask Questions

Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization


Oct 21, 2021
Adyasha Maharana, Mohit Bansal

* EMNLP 2021 (16 pages) 

  Access Paper or Ask Questions

Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks


Sep 30, 2021
Yichen Jiang, Mohit Bansal

* EMNLP 2021 (13 pages) 

  Access Paper or Ask Questions

iFacetSum: Coreference-based Interactive Faceted Summarization for Multi-Document Exploration


Sep 23, 2021
Eran Hirsch, Alon Eirew, Ori Shapira, Avi Caciularu, Arie Cattan, Ori Ernst, Ramakanth Pasunuru, Hadar Ronen, Mohit Bansal, Ido Dagan

* Proceedings of EMNLP 2021, System Demonstrations. 7 pages and an appendix 

  Access Paper or Ask Questions

Finding a Balanced Degree of Automation for Summary Evaluation


Sep 23, 2021
Shiyue Zhang, Mohit Bansal

* EMNLP 2021 (17 pages) 

  Access Paper or Ask Questions

ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback


Aug 02, 2021
Shiyue Zhang, Benjamin Frey, Mohit Bansal

* ACL 2021 Demo (8 pages) 

  Access Paper or Ask Questions

MTVR: Multilingual Moment Retrieval in Videos


Jul 30, 2021
Jie Lei, Tamara L. Berg, Mohit Bansal

* ACL 2021 (9 pages, 4 figures) 

  Access Paper or Ask Questions

EmailSum: Abstractive Email Thread Summarization


Jul 30, 2021
Shiyue Zhang, Asli Celikyilmaz, Jianfeng Gao, Mohit Bansal

* ACL 2021 (15 pages) 

  Access Paper or Ask Questions

QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries


Jul 20, 2021
Jie Lei, Tamara L. Berg, Mohit Bansal

* 17 pages, 11 figures, 5 tables 

  Access Paper or Ask Questions

How Much Can CLIP Benefit Vision-and-Language Tasks?


Jul 13, 2021
Sheng Shen, Liunian Harold Li, Hao Tan, Mohit Bansal, Anna Rohrbach, Kai-Wei Chang, Zhewei Yao, Kurt Keutzer

* 14 pages 

  Access Paper or Ask Questions

VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer


Jul 06, 2021
Zineng Tang, Jaemin Cho, Hao Tan, Mohit Bansal

* 18 pages (5 figures, 10 tables) 

  Access Paper or Ask Questions

VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning


Jun 21, 2021
Hao Tan, Jie Lei, Thomas Wolf, Mohit Bansal

* Under review, 23 Pages 

  Access Paper or Ask Questions

Disentangling Online Chats with DAG-Structured LSTMs


Jun 16, 2021
Duccio Pappadopulo, Lisa Bauer, Marco Farina, Ozan İrsoy, Mohit Bansal

* 8 pages, 1 figure. Accepted at *SEM 2021 

  Access Paper or Ask Questions

An Empirical Survey of Data Augmentation for Limited Data Learning in NLP


Jun 14, 2021
Jiaao Chen, Derek Tam, Colin Raffel, Mohit Bansal, Diyi Yang


  Access Paper or Ask Questions

VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation


Jun 08, 2021
Linjie Li, Jie Lei, Zhe Gan, Licheng Yu, Yen-Chun Chen, Rohit Pillai, Yu Cheng, Luowei Zhou, Xin Eric Wang, William Yang Wang, Tamara Lee Berg, Mohit Bansal, Jingjing Liu, Lijuan Wang, Zicheng Liu

* VALUE is available at https://value-leaderboard.github.io/ 

  Access Paper or Ask Questions

multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning


Jun 02, 2021
Swarnadeep Saha, Prateek Yadav, Mohit Bansal

* NAACL 2021 (16 pages) 

  Access Paper or Ask Questions

Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization


Jun 02, 2021
Yichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao

* NAACL 2021 (14 pages) 

  Access Paper or Ask Questions

Search Methods for Sufficient, Socially-Aligned Feature Importance Explanations with In-Distribution Counterfactuals


Jun 01, 2021
Peter Hase, Harry Xie, Mohit Bansal

* 26 pages, 4 figures, 8 tables 

  Access Paper or Ask Questions

Improving Generation and Evaluation of Visual Stories via Semantic Consistency


May 20, 2021
Adyasha Maharana, Darryl Hannan, Mohit Bansal

* NAACL 2021 (16 pages) 

  Access Paper or Ask Questions

Identify, Align, and Integrate: Matching Knowledge Graphs to Commonsense Reasoning Tasks


Apr 20, 2021
Lisa Bauer, Mohit Bansal

* EACL 2021 (14 pages, 2 figures, 10 tables) 

  Access Paper or Ask Questions

Hidden Biases in Unreliable News Detection Datasets


Apr 20, 2021
Xiang Zhou, Heba Elfardy, Christos Christodoulopoulos, Thomas Butler, Mohit Bansal

* EACL 2021 (11 pages, 3 figures, 8 tables) 

  Access Paper or Ask Questions

Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information


Apr 19, 2021
Jialu Li, Hao Tan, Mohit Bansal

* NAACL 2021 (10 pages) 

  Access Paper or Ask Questions

Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning


Apr 18, 2021
Xiang Zhou, Yixin Nie, Mohit Bansal

* 13 pages, 2 figures, 8 tables 

  Access Paper or Ask Questions

ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning


Apr 17, 2021
Swarnadeep Saha, Prateek Yadav, Lisa Bauer, Mohit Bansal

* 25 pages, 10 tables, 24 figures 

  Access Paper or Ask Questions

Dynabench: Rethinking Benchmarking in NLP


Apr 07, 2021
Douwe Kiela, Max Bartolo, Yixin Nie, Divyansh Kaushik, Atticus Geiger, Zhengxuan Wu, Bertie Vidgen, Grusha Prasad, Amanpreet Singh, Pratik Ringshia, Zhiyi Ma, Tristan Thrush, Sebastian Riedel, Zeerak Waseem, Pontus Stenetorp, Robin Jia, Mohit Bansal, Christopher Potts, Adina Williams

* NAACL 2021 

  Access Paper or Ask Questions

FixMyPose: Pose Correctional Captioning and Retrieval


Apr 04, 2021
Hyounghun Kim, Abhay Zala, Graham Burri, Mohit Bansal

* AAAI 2021 (18 pages, 16 figures; webpage: https://fixmypose-unc.github.io/

  Access Paper or Ask Questions

Improving and Simplifying Pattern Exploiting Training


Mar 22, 2021
Derek Tam, Rakesh R Menon, Mohit Bansal, Shashank Srivastava, Colin Raffel

* 11 pages, 2 figures 

  Access Paper or Ask Questions

Dual Reinforcement-Based Specification Generation for Image De-Rendering


Mar 02, 2021
Ramakanth Pasunuru, David Rosenberg, Gideon Mann, Mohit Bansal

* AAAI 2021 Scientific Document Understanding Workshop (9 pages) 

  Access Paper or Ask Questions