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 Yejin Choi

Yejin Choi

"I'm Not Mad": Commonsense Implications of Negation and Contradiction


Apr 13, 2021
Liwei Jiang, Antoine Bosselut, Chandra Bhagavatula, Yejin Choi

Figure 1 for "I'm Not Mad": Commonsense Implications of Negation and Contradiction
Figure 2 for "I'm Not Mad": Commonsense Implications of Negation and Contradiction
Figure 3 for "I'm Not Mad": Commonsense Implications of Negation and Contradiction
Figure 4 for "I'm Not Mad": Commonsense Implications of Negation and Contradiction

  Access Paper or Ask Questions

UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark


Mar 24, 2021
Nicholas Lourie, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi

Figure 1 for UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
Figure 2 for UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
Figure 3 for UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
Figure 4 for UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
* 27 pages, 19 figures, 34 tables. Accepted to AAAI 2021. For associated code and data see https://github.com/allenai/rainbow 
  Access Paper or Ask Questions

NaturalProofs: Mathematical Theorem Proving in Natural Language


Mar 24, 2021
Sean Welleck, Jiacheng Liu, Ronan Le Bras, Hannaneh Hajishirzi, Yejin Choi, Kyunghyun Cho

Figure 1 for NaturalProofs: Mathematical Theorem Proving in Natural Language
Figure 2 for NaturalProofs: Mathematical Theorem Proving in Natural Language
Figure 3 for NaturalProofs: Mathematical Theorem Proving in Natural Language
Figure 4 for NaturalProofs: Mathematical Theorem Proving in Natural Language

  Access Paper or Ask Questions

Contrastive Explanations for Model Interpretability


Mar 02, 2021
Alon Jacovi, Swabha Swayamdipta, Shauli Ravfogel, Yanai Elazar, Yejin Choi, Yoav Goldberg


  Access Paper or Ask Questions

MAUVE: Human-Machine Divergence Curves for Evaluating Open-Ended Text Generation


Feb 02, 2021
Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Yejin Choi, Zaid Harchaoui

Figure 1 for MAUVE: Human-Machine Divergence Curves for Evaluating Open-Ended Text Generation
Figure 2 for MAUVE: Human-Machine Divergence Curves for Evaluating Open-Ended Text Generation
Figure 3 for MAUVE: Human-Machine Divergence Curves for Evaluating Open-Ended Text Generation
Figure 4 for MAUVE: Human-Machine Divergence Curves for Evaluating Open-Ended Text Generation

  Access Paper or Ask Questions

MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations


Feb 02, 2021
Yao Dou, Maxwell Forbes, Ari Holtzman, Yejin Choi

Figure 1 for MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations
Figure 2 for MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations
Figure 3 for MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations
Figure 4 for MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations
* 7 pages, AAAI-21 
  Access Paper or Ask Questions

Challenges in Automated Debiasing for Toxic Language Detection


Jan 29, 2021
Xuhui Zhou, Maarten Sap, Swabha Swayamdipta, Noah A. Smith, Yejin Choi

Figure 1 for Challenges in Automated Debiasing for Toxic Language Detection
Figure 2 for Challenges in Automated Debiasing for Toxic Language Detection
Figure 3 for Challenges in Automated Debiasing for Toxic Language Detection
Figure 4 for Challenges in Automated Debiasing for Toxic Language Detection
* EACL 2021 
  Access Paper or Ask Questions

GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation


Jan 17, 2021
Daniel Khashabi, Gabriel Stanovsky, Jonathan Bragg, Nicholas Lourie, Jungo Kasai, Yejin Choi, Noah A. Smith, Daniel S. Weld

Figure 1 for GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation
Figure 2 for GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation
Figure 3 for GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation
Figure 4 for GENIE: A Leaderboard for Human-in-the-Loop Evaluation of Text Generation

  Access Paper or Ask Questions

VinVL: Making Visual Representations Matter in Vision-Language Models


Jan 02, 2021
Pengchuan Zhang, Xiujun Li, Xiaowei Hu, Jianwei Yang, Lei Zhang, Lijuan Wang, Yejin Choi, Jianfeng Gao

Figure 1 for VinVL: Making Visual Representations Matter in Vision-Language Models
Figure 2 for VinVL: Making Visual Representations Matter in Vision-Language Models
Figure 3 for VinVL: Making Visual Representations Matter in Vision-Language Models
Figure 4 for VinVL: Making Visual Representations Matter in Vision-Language Models

  Access Paper or Ask Questions

On-the-Fly Attention Modularization for Neural Generation


Jan 02, 2021
Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang, Antoine Bosselut, Jackie Chi Kit Cheung, Yejin Choi

Figure 1 for On-the-Fly Attention Modularization for Neural Generation
Figure 2 for On-the-Fly Attention Modularization for Neural Generation
Figure 3 for On-the-Fly Attention Modularization for Neural Generation
Figure 4 for On-the-Fly Attention Modularization for Neural Generation
* 10 pages, 3 figures 
  Access Paper or Ask Questions

Understanding Few-Shot Commonsense Knowledge Models


Jan 01, 2021
Jeff Da, Ronan Le Bras, Ximing Lu, Yejin Choi, Antoine Bosselut

Figure 1 for Understanding Few-Shot Commonsense Knowledge Models
Figure 2 for Understanding Few-Shot Commonsense Knowledge Models
Figure 3 for Understanding Few-Shot Commonsense Knowledge Models
Figure 4 for Understanding Few-Shot Commonsense Knowledge Models

  Access Paper or Ask Questions

Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences


Dec 31, 2020
Denis Emelin, Ronan Le Bras, Jena D. Hwang, Maxwell Forbes, Yejin Choi

Figure 1 for Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
Figure 2 for Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
Figure 3 for Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
Figure 4 for Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
* For the 'Moral Stories' dataset, see https://github.com/demelin/moral_stories 
  Access Paper or Ask Questions

Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision


Dec 14, 2020
Faeze Brahman, Vered Shwartz, Rachel Rudinger, Yejin Choi

Figure 1 for Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
Figure 2 for Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
Figure 3 for Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
Figure 4 for Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
* AAAI 2021 
  Access Paper or Ask Questions

Edited Media Understanding: Reasoning About Implications of Manipulated Images


Dec 08, 2020
Jeff Da, Maxwell Forbes, Rowan Zellers, Anthony Zheng, Jena D. Hwang, Antoine Bosselut, Yejin Choi

Figure 1 for Edited Media Understanding: Reasoning About Implications of Manipulated Images
Figure 2 for Edited Media Understanding: Reasoning About Implications of Manipulated Images
Figure 3 for Edited Media Understanding: Reasoning About Implications of Manipulated Images
Figure 4 for Edited Media Understanding: Reasoning About Implications of Manipulated Images

  Access Paper or Ask Questions

Social Chemistry 101: Learning to Reason about Social and Moral Norms


Nov 01, 2020
Maxwell Forbes, Jena D. Hwang, Vered Shwartz, Maarten Sap, Yejin Choi

Figure 1 for Social Chemistry 101: Learning to Reason about Social and Moral Norms
Figure 2 for Social Chemistry 101: Learning to Reason about Social and Moral Norms
Figure 3 for Social Chemistry 101: Learning to Reason about Social and Moral Norms
Figure 4 for Social Chemistry 101: Learning to Reason about Social and Moral Norms
* Published at EMNLP 2020 
  Access Paper or Ask Questions

PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction


Oct 26, 2020
Xinyao Ma, Maarten Sap, Hannah Rashkin, Yejin Choi

Figure 1 for PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction
Figure 2 for PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction
Figure 3 for PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction
Figure 4 for PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction
* EMNLP 2020 
  Access Paper or Ask Questions

NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints


Oct 24, 2020
Ximing Lu, Peter West, Rowan Zellers, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi

Figure 1 for NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
Figure 2 for NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
Figure 3 for NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
Figure 4 for NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints

  Access Paper or Ask Questions

Go Figure! A Meta Evaluation of Factuality in Summarization


Oct 24, 2020
Saadia Gabriel, Asli Celikyilmaz, Rahul Jha, Yejin Choi, Jianfeng Gao

Figure 1 for Go Figure! A Meta Evaluation of Factuality in Summarization
Figure 2 for Go Figure! A Meta Evaluation of Factuality in Summarization
Figure 3 for Go Figure! A Meta Evaluation of Factuality in Summarization
Figure 4 for Go Figure! A Meta Evaluation of Factuality in Summarization

  Access Paper or Ask Questions

Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning


Oct 20, 2020
Lianhui Qin, Vered Shwartz, Peter West, Chandra Bhagavatula, Jena Hwang, Ronan Le Bras, Antoine Bosselut, Yejin Choi

Figure 1 for Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
Figure 2 for Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
Figure 3 for Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
Figure 4 for Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
* EMNLP 2020 
  Access Paper or Ask Questions

Reflective Decoding: Unsupervised Paraphrasing and Abductive Reasoning


Oct 16, 2020
Peter West, Ximing Lu, Ari Holtzman, Chandra Bhagavatula, Jena Hwang, Yejin Choi

Figure 1 for Reflective Decoding: Unsupervised Paraphrasing and Abductive Reasoning
Figure 2 for Reflective Decoding: Unsupervised Paraphrasing and Abductive Reasoning
Figure 3 for Reflective Decoding: Unsupervised Paraphrasing and Abductive Reasoning
Figure 4 for Reflective Decoding: Unsupervised Paraphrasing and Abductive Reasoning

  Access Paper or Ask Questions

Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics


Oct 15, 2020
Swabha Swayamdipta, Roy Schwartz, Nicholas Lourie, Yizhong Wang, Hannaneh Hajishirzi, Noah A. Smith, Yejin Choi

Figure 1 for Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
Figure 2 for Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
Figure 3 for Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
Figure 4 for Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
* Proceedings of EMNLP 2020 
  Access Paper or Ask Questions

Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs


Oct 15, 2020
Ana Marasović, Chandra Bhagavatula, Jae Sung Park, Ronan Le Bras, Noah A. Smith, Yejin Choi

Figure 1 for Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
Figure 2 for Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
Figure 3 for Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
Figure 4 for Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
* Accepted to Findings of EMNLP 
  Access Paper or Ask Questions

COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs


Oct 12, 2020
Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, Yejin Choi

Figure 1 for COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
Figure 2 for COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
Figure 3 for COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
Figure 4 for COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs

  Access Paper or Ask Questions

Paragraph-Level Commonsense Transformers with Recurrent Memory


Oct 04, 2020
Saadia Gabriel, Chandra Bhagavatula, Vered Shwartz, Ronan Le Bras, Maxwell Forbes, Yejin Choi

Figure 1 for Paragraph-Level Commonsense Transformers with Recurrent Memory
Figure 2 for Paragraph-Level Commonsense Transformers with Recurrent Memory
Figure 3 for Paragraph-Level Commonsense Transformers with Recurrent Memory
Figure 4 for Paragraph-Level Commonsense Transformers with Recurrent Memory

  Access Paper or Ask Questions

RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models


Sep 25, 2020
Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, Noah A. Smith

Figure 1 for RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Figure 2 for RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Figure 3 for RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
Figure 4 for RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models
* Findings in EMNLP 2020 
  Access Paper or Ask Questions

Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes


Aug 20, 2020
Nicholas Lourie, Ronan Le Bras, Yejin Choi

Figure 1 for Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes
Figure 2 for Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes
Figure 3 for Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes
Figure 4 for Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes
* 16 pages, 15 tables, 8 figures. For associated code and data, see https://github.com/allenai/scruples 
  Access Paper or Ask Questions

Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks


May 18, 2020
Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, Yejin Choi, Jianfeng Gao

Figure 1 for Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
Figure 2 for Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
Figure 3 for Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
Figure 4 for Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks
* Code and pre-trained models are released: https://github.com/microsoft/Oscar 
  Access Paper or Ask Questions

PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking


Apr 30, 2020
Hannah Rashkin, Asli Celikyilmaz, Yejin Choi, Jianfeng Gao

Figure 1 for PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking
Figure 2 for PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking
Figure 3 for PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking
Figure 4 for PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking

  Access Paper or Ask Questions