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 Kyunghyun Cho

Kyunghyun Cho

Comparing Test Sets with Item Response Theory


Jun 01, 2021
Clara Vania, Phu Mon Htut, William Huang, Dhara Mungra, Richard Yuanzhe Pang, Jason Phang, Haokun Liu, Kyunghyun Cho, Samuel R. Bowman

Figure 1 for Comparing Test Sets with Item Response Theory
Figure 2 for Comparing Test Sets with Item Response Theory
Figure 3 for Comparing Test Sets with Item Response Theory
Figure 4 for Comparing Test Sets with Item Response Theory
* ACL 2021 
  Access Paper or Ask Questions

True Few-Shot Learning with Language Models


May 24, 2021
Ethan Perez, Douwe Kiela, Kyunghyun Cho

Figure 1 for True Few-Shot Learning with Language Models
Figure 2 for True Few-Shot Learning with Language Models
Figure 3 for True Few-Shot Learning with Language Models
Figure 4 for True Few-Shot Learning with Language Models
* Code at https://github.com/ethanjperez/true_few_shot 
  Access Paper or Ask Questions

KLUE: Korean Language Understanding Evaluation


May 21, 2021
Sungjoon Park, Jihyung Moon, Sungdong Kim, Won Ik Cho, Jiyoon Han, Jangwon Park, Chisung Song, Junseong Kim, Yongsook Song, Taehwan Oh, Joohong Lee, Juhyun Oh, Sungwon Lyu, Younghoon Jeong, Inkwon Lee, Sangwoo Seo, Dongjun Lee, Hyunwoo Kim, Myeonghwa Lee, Seongbo Jang, Seungwon Do, Sunkyoung Kim, Kyungtae Lim, Jongwon Lee, Kyumin Park, Jamin Shin, Seonghyun Kim, Lucy Park, Alice Oh, Jung-Woo Ha, Kyunghyun Cho

Figure 1 for KLUE: Korean Language Understanding Evaluation
Figure 2 for KLUE: Korean Language Understanding Evaluation
Figure 3 for KLUE: Korean Language Understanding Evaluation
Figure 4 for KLUE: Korean Language Understanding Evaluation
* 76 pages, 10 figures, 36 tables 
  Access Paper or Ask Questions

Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction


Apr 15, 2021
Manling Li, Sha Li, Zhenhailong Wang, Lifu Huang, Kyunghyun Cho, Heng Ji, Jiawei Han, Clare Voss

Figure 1 for Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction
Figure 2 for Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction
Figure 3 for Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction
Figure 4 for Future is not One-dimensional: Graph Modeling based Complex Event Schema Induction for Event Prediction

  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

Rissanen Data Analysis: Examining Dataset Characteristics via Description Length


Mar 05, 2021
Ethan Perez, Douwe Kiela, Kyunghyun Cho

Figure 1 for Rissanen Data Analysis: Examining Dataset Characteristics via Description Length
Figure 2 for Rissanen Data Analysis: Examining Dataset Characteristics via Description Length
Figure 3 for Rissanen Data Analysis: Examining Dataset Characteristics via Description Length
Figure 4 for Rissanen Data Analysis: Examining Dataset Characteristics via Description Length
* Code at https://github.com/ethanjperez/rda along with a script to run RDA on your own dataset 
  Access Paper or Ask Questions

Online hyperparameter optimization by real-time recurrent learning


Feb 15, 2021
Daniel Jiwoong Im, Cristina Savin, Kyunghyun Cho

Figure 1 for Online hyperparameter optimization by real-time recurrent learning
Figure 2 for Online hyperparameter optimization by real-time recurrent learning
Figure 3 for Online hyperparameter optimization by real-time recurrent learning
Figure 4 for Online hyperparameter optimization by real-time recurrent learning

  Access Paper or Ask Questions

Self-Supervised Equivariant Scene Synthesis from Video


Feb 01, 2021
Cinjon Resnick, Or Litany, Cosmas Heiß, Hugo Larochelle, Joan Bruna, Kyunghyun Cho

Figure 1 for Self-Supervised Equivariant Scene Synthesis from Video
Figure 2 for Self-Supervised Equivariant Scene Synthesis from Video
Figure 3 for Self-Supervised Equivariant Scene Synthesis from Video
Figure 4 for Self-Supervised Equivariant Scene Synthesis from Video
* arXiv admin note: text overlap with arXiv:2011.05787 
  Access Paper or Ask Questions

Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization


Dec 28, 2020
Stanislaw Jastrzebski, Devansh Arpit, Oliver Astrand, Giancarlo Kerg, Huan Wang, Caiming Xiong, Richard Socher, Kyunghyun Cho, Krzysztof Geras

Figure 1 for Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Figure 2 for Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Figure 3 for Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
Figure 4 for Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization
* The last two authors contributed equally 
  Access Paper or Ask Questions

A Study on the Autoregressive and non-Autoregressive Multi-label Learning


Dec 03, 2020
Elham J. Barezi, Iacer Calixto, Kyunghyun Cho, Pascale Fung


  Access Paper or Ask Questions

Differences between human and machine perception in medical diagnosis


Nov 28, 2020
Taro Makino, Stanislaw Jastrzebski, Witold Oleszkiewicz, Celin Chacko, Robin Ehrenpreis, Naziya Samreen, Chloe Chhor, Eric Kim, Jiyon Lee, Kristine Pysarenko, Beatriu Reig, Hildegard Toth, Divya Awal, Linda Du, Alice Kim, James Park, Daniel K. Sodickson, Laura Heacock, Linda Moy, Kyunghyun Cho, Krzysztof J. Geras

Figure 1 for Differences between human and machine perception in medical diagnosis
Figure 2 for Differences between human and machine perception in medical diagnosis
Figure 3 for Differences between human and machine perception in medical diagnosis
Figure 4 for Differences between human and machine perception in medical diagnosis

  Access Paper or Ask Questions

Learned Equivariant Rendering without Transformation Supervision


Nov 11, 2020
Cinjon Resnick, Or Litany, Hugo Larochelle, Joan Bruna, Kyunghyun Cho

Figure 1 for Learned Equivariant Rendering without Transformation Supervision
Figure 2 for Learned Equivariant Rendering without Transformation Supervision
Figure 3 for Learned Equivariant Rendering without Transformation Supervision
Figure 4 for Learned Equivariant Rendering without Transformation Supervision
* Workshop on Differentiable Vision, Graphics, and Physics in Machine Learning at NeurIPS 2020 
  Access Paper or Ask Questions

Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning


Nov 01, 2020
Jon Ander Campos, Kyunghyun Cho, Arantxa Otegi, Aitor Soroa, Gorka Azkune, Eneko Agirre

Figure 1 for Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning
Figure 2 for Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning
Figure 3 for Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning
Figure 4 for Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning
* Accepted at COLING 2020. 11 pages, 5 figures 
  Access Paper or Ask Questions

Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search


Oct 14, 2020
Gyuwan Kim, Kyunghyun Cho

Figure 1 for Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
Figure 2 for Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
Figure 3 for Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
* 11 pages, 4 figures 
  Access Paper or Ask Questions

Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule


Oct 08, 2020
Shuhei Kurita, Kyunghyun Cho

Figure 1 for Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule
Figure 2 for Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule
Figure 3 for Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule
Figure 4 for Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule
* 13 pages, 8 figures 
  Access Paper or Ask Questions

SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness


Oct 04, 2020
Nathan Ng, Kyunghyun Cho, Marzyeh Ghassemi

Figure 1 for SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness
Figure 2 for SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness
Figure 3 for SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness
Figure 4 for SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness
* 16 pages, 8 figures, to be published in EMNLP 2020 
  Access Paper or Ask Questions

Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms


Sep 19, 2020
Nan Wu, Zhe Huang, Yiqiu Shen, Jungkyu Park, Jason Phang, Taro Makino, S. Gene Kim, Kyunghyun Cho, Laura Heacock, Linda Moy, Krzysztof J. Geras

Figure 1 for Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms
Figure 2 for Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms
Figure 3 for Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms
Figure 4 for Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms

  Access Paper or Ask Questions

Evaluating representations by the complexity of learning low-loss predictors


Sep 15, 2020
William F. Whitney, Min Jae Song, David Brandfonbrener, Jaan Altosaar, Kyunghyun Cho

Figure 1 for Evaluating representations by the complexity of learning low-loss predictors
Figure 2 for Evaluating representations by the complexity of learning low-loss predictors
Figure 3 for Evaluating representations by the complexity of learning low-loss predictors

  Access Paper or Ask Questions

A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation


Sep 15, 2020
Moin Nadeem, Tianxing He, Kyunghyun Cho, James Glass

Figure 1 for A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
Figure 2 for A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
Figure 3 for A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
Figure 4 for A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation
* To appear at AACL 2020; 9 pages, 12 figures, 2 tables 
  Access Paper or Ask Questions

Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation


Sep 15, 2020
Jason Lee, Raphael Shu, Kyunghyun Cho

Figure 1 for Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation
Figure 2 for Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation
Figure 3 for Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation
Figure 4 for Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation
* Accepted to EMNLP 2020 
  Access Paper or Ask Questions

A Framework For Contrastive Self-Supervised Learning And Designing A New Approach


Aug 31, 2020
William Falcon, Kyunghyun Cho

Figure 1 for A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
Figure 2 for A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
Figure 3 for A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
Figure 4 for A Framework For Contrastive Self-Supervised Learning And Designing A New Approach

  Access Paper or Ask Questions

VisualSem: a high-quality knowledge graph for vision and language


Aug 20, 2020
Houda Alberts, Teresa Huang, Yash Deshpande, Yibo Liu, Kyunghyun Cho, Clara Vania, Iacer Calixto

Figure 1 for VisualSem: a high-quality knowledge graph for vision and language
Figure 2 for VisualSem: a high-quality knowledge graph for vision and language
Figure 3 for VisualSem: a high-quality knowledge graph for vision and language
Figure 4 for VisualSem: a high-quality knowledge graph for vision and language
* 11 pages, 5 figures, 6 tables 
  Access Paper or Ask Questions

AdapterHub: A Framework for Adapting Transformers


Jul 15, 2020
Jonas Pfeiffer, Andreas Rücklé, Clifton Poth, Aishwarya Kamath, Ivan Vulić, Sebastian Ruder, Kyunghyun Cho, Iryna Gurevych

Figure 1 for AdapterHub: A Framework for Adapting Transformers
Figure 2 for AdapterHub: A Framework for Adapting Transformers
Figure 3 for AdapterHub: A Framework for Adapting Transformers
Figure 4 for AdapterHub: A Framework for Adapting Transformers

  Access Paper or Ask Questions

Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset


Jul 14, 2020
Edwin Zhang, Nikhil Gupta, Raphael Tang, Xiao Han, Ronak Pradeep, Kuang Lu, Yue Zhang, Rodrigo Nogueira, Kyunghyun Cho, Hui Fang, Jimmy Lin

Figure 1 for Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset
Figure 2 for Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset
* arXiv admin note: text overlap with arXiv:2004.05125 
  Access Paper or Ask Questions

MLE-guided parameter search for task loss minimization in neural sequence modeling


Jun 04, 2020
Sean Welleck, Kyunghyun Cho

Figure 1 for MLE-guided parameter search for task loss minimization in neural sequence modeling
Figure 2 for MLE-guided parameter search for task loss minimization in neural sequence modeling
Figure 3 for MLE-guided parameter search for task loss minimization in neural sequence modeling
Figure 4 for MLE-guided parameter search for task loss minimization in neural sequence modeling

  Access Paper or Ask Questions

AdapterFusion: Non-Destructive Task Composition for Transfer Learning


May 01, 2020
Jonas Pfeiffer, Aishwarya Kamath, Andreas Rücklé, Kyunghyun Cho, Iryna Gurevych

Figure 1 for AdapterFusion: Non-Destructive Task Composition for Transfer Learning
Figure 2 for AdapterFusion: Non-Destructive Task Composition for Transfer Learning
Figure 3 for AdapterFusion: Non-Destructive Task Composition for Transfer Learning
Figure 4 for AdapterFusion: Non-Destructive Task Composition for Transfer Learning

  Access Paper or Ask Questions