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 Ashish Sabharwal

Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?


Jun 02, 2021
Jieyu Zhao, Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Kai-Wei Chang

* 9 pages, Findings of ACL-IJCNLP 2021 

  Access Paper or Ask Questions

GooAQ: Open Question Answering with Diverse Answer Types


Apr 18, 2021
Daniel Khashabi, Amos Ng, Tushar Khot, Ashish Sabharwal, Hannaneh Hajishirzi, Chris Callison-Burch


  Access Paper or Ask Questions

Multi-Modal Answer Validation for Knowledge-Based VQA


Mar 23, 2021
Jialin Wu, Jiasen Lu, Ashish Sabharwal, Roozbeh Mottaghi


  Access Paper or Ask Questions

Think you have Solved Direct-Answer Question Answering? Try ARC-DA, the Direct-Answer AI2 Reasoning Challenge


Feb 05, 2021
Sumithra Bhakthavatsalam, Daniel Khashabi, Tushar Khot, Bhavana Dalvi Mishra, Kyle Richardson, Ashish Sabharwal, Carissa Schoenick, Oyvind Tafjord, Peter Clark


  Access Paper or Ask Questions

ReadOnce Transformers: Reusable Representations of Text for Transformers


Oct 24, 2020
Shih-Ting Lin, Ashish Sabharwal, Tushar Khot


  Access Paper or Ask Questions

Temporal Reasoning on Implicit Events from Distant Supervision


Oct 24, 2020
Ben Zhou, Kyle Richardson, Qiang Ning, Tushar Khot, Ashish Sabharwal, Dan Roth


  Access Paper or Ask Questions

UnQovering Stereotyping Biases via Underspecified Questions


Oct 10, 2020
Tao Li, Tushar Khot, Daniel Khashabi, Ashish Sabharwal, Vivek Srikumar

* Accepted at Findings of EMNLP 2020 

  Access Paper or Ask Questions

Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models


Sep 01, 2020
Tushar Khot, Daniel Khashabi, Kyle Richardson, Peter Clark, Ashish Sabharwal


  Access Paper or Ask Questions

Belief Propagation Neural Networks


Jul 01, 2020
Jonathan Kuck, Shuvam Chakraborty, Hao Tang, Rachel Luo, Jiaming Song, Ashish Sabharwal, Stefano Ermon


  Access Paper or Ask Questions

Measuring and Reducing Non-Multifact Reasoning in Multi-hop Question Answering


May 02, 2020
Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal


  Access Paper or Ask Questions

UnifiedQA: Crossing Format Boundaries With a Single QA System


May 02, 2020
Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Oyvind Tafjord, Peter Clark, Hannaneh Hajishirzi


  Access Paper or Ask Questions

A Simple Yet Strong Pipeline for HotpotQA


Apr 14, 2020
Dirk Groeneveld, Tushar Khot, Mausam, Ashish Sabharwal


  Access Paper or Ask Questions

Natural Perturbation for Robust Question Answering


Apr 09, 2020
Daniel Khashabi, Tushar Khot, Ashish Sabharwal


  Access Paper or Ask Questions

Adversarial Filters of Dataset Biases


Feb 20, 2020
Ronan Le Bras, Swabha Swayamdipta, Chandra Bhagavatula, Rowan Zellers, Matthew E. Peters, Ashish Sabharwal, Yejin Choi


  Access Paper or Ask Questions

What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge


Dec 31, 2019
Kyle Richardson, Ashish Sabharwal

* work in progress 

  Access Paper or Ask Questions

Approximating the Permanent by Sampling from Adaptive Partitions


Nov 26, 2019
Jonathan Kuck, Tri Dao, Hamid Rezatofighi, Ashish Sabharwal, Stefano Ermon

* 19 pages 

  Access Paper or Ask Questions

Not All Claims are Created Equal: Choosing the Right Approach to Assess Your Hypotheses


Nov 10, 2019
Erfan Sadeqi Azer, Daniel Khashabi, Ashish Sabharwal, Dan Roth


  Access Paper or Ask Questions

QASC: A Dataset for Question Answering via Sentence Composition


Oct 25, 2019
Tushar Khot, Peter Clark, Michal Guerquin, Peter Jansen, Ashish Sabharwal


  Access Paper or Ask Questions

AdaWISH: Faster Discrete Integration via Adaptive Quantiles


Oct 13, 2019
Fan Ding, Hanjing Wang, Ashish Sabharwal, Yexiang Xue


  Access Paper or Ask Questions

What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering


Sep 19, 2019
Tushar Khot, Ashish Sabharwal, Peter Clark

* EMNLP 2019 

  Access Paper or Ask Questions

Probing Natural Language Inference Models through Semantic Fragments


Sep 16, 2019
Kyle Richardson, Hai Hu, Lawrence S. Moss, Ashish Sabharwal


  Access Paper or Ask Questions

From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project


Sep 11, 2019
Peter Clark, Oren Etzioni, Daniel Khashabi, Tushar Khot, Bhavana Dalvi Mishra, Kyle Richardson, Ashish Sabharwal, Carissa Schoenick, Oyvind Tafjord, Niket Tandon, Sumithra Bhakthavatsalam, Dirk Groeneveld, Michal Guerquin, Michael Schmitz

* v2 add authors (content unchanged) 

  Access Paper or Ask Questions

Question Answering as Global Reasoning over Semantic Abstractions


Jun 09, 2019
Daniel Khashabi, Tushar Khot, Ashish Sabharwal, Dan Roth

* Appeared in AAAI'18 

  Access Paper or Ask Questions

Repurposing Entailment for Multi-Hop Question Answering Tasks


Apr 20, 2019
Harsh Trivedi, Heeyoung Kwon, Tushar Khot, Ashish Sabharwal, Niranjan Balasubramanian

* Accepted at NAACL'19 

  Access Paper or Ask Questions

On the Capabilities and Limitations of Reasoning for Natural Language Understanding


Jan 08, 2019
Daniel Khashabi, Erfan Sadeqi Azer, Tushar Khot, Ashish Sabharwal, Dan Roth


  Access Paper or Ask Questions

QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships


Nov 20, 2018
Oyvind Tafjord, Peter Clark, Matt Gardner, Wen-tau Yih, Ashish Sabharwal

* 9 pages, AAAI 2019 

  Access Paper or Ask Questions

Exploiting Explicit Paths for Multi-hop Reading Comprehension


Nov 02, 2018
Souvik Kundu, Tushar Khot, Ashish Sabharwal


  Access Paper or Ask Questions

Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering


Sep 08, 2018
Todor Mihaylov, Peter Clark, Tushar Khot, Ashish Sabharwal

* Published as conference long paper at EMNLP 2018 

  Access Paper or Ask Questions