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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
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

* 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


  Access Paper or Ask Questions

Learned Equivariant Rendering without Transformation Supervision

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

* 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

* 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

* 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

* 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

* 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


  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


  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

* 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

* 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


  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

* 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


  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

* 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


  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


  Access Paper or Ask Questions

Learning Non-Monotonic Automatic Post-Editing of Translations from Human Orderings

Apr 29, 2020
António Góis, Kyunghyun Cho, André Martins

* Accepted at EAMT 2020; dataset available here: https://github.com/antoniogois/keystrokes_ape 

  Access Paper or Ask Questions

Learning to Learn Morphological Inflection for Resource-Poor Languages

Apr 28, 2020
Katharina Kann, Samuel R. Bowman, Kyunghyun Cho

* AAAI 2020 

  Access Paper or Ask Questions

Rapidly Bootstrapping a Question Answering Dataset for COVID-19

Apr 23, 2020
Raphael Tang, Rodrigo Nogueira, Edwin Zhang, Nikhil Gupta, Phuong Cam, Kyunghyun Cho, Jimmy Lin


  Access Paper or Ask Questions

Rapidly Deploying a Neural Search Engine for the COVID-19 Open Research Dataset: Preliminary Thoughts and Lessons Learned

Apr 10, 2020
Edwin Zhang, Nikhil Gupta, Rodrigo Nogueira, Kyunghyun Cho, Jimmy Lin


  Access Paper or Ask Questions

Asking and Answering Questions to Evaluate the Factual Consistency of Summaries

Apr 08, 2020
Alex Wang, Kyunghyun Cho, Mike Lewis

* ACL 2020 

  Access Paper or Ask Questions

Understanding the robustness of deep neural network classifiers for breast cancer screening

Mar 23, 2020
Witold Oleszkiewicz, Taro Makino, Stanisław Jastrzębski, Tomasz Trzciński, Linda Moy, Kyunghyun Cho, Laura Heacock, Krzysztof J. Geras

* Accepted as a workshop paper at AI4AH, ICLR 2020 

  Access Paper or Ask Questions

Unsupervised Question Decomposition for Question Answering

Feb 22, 2020
Ethan Perez, Patrick Lewis, Wen-tau Yih, Kyunghyun Cho, Douwe Kiela


  Access Paper or Ask Questions

The Break-Even Point on Optimization Trajectories of Deep Neural Networks

Feb 21, 2020
Stanislaw Jastrzebski, Maciej Szymczak, Stanislav Fort, Devansh Arpit, Jacek Tabor, Kyunghyun Cho, Krzysztof Geras

* Accepted as a spotlight at ICLR 2020. The last two authors contributed equally 

  Access Paper or Ask Questions

On the Discrepancy between Density Estimation and Sequence Generation

Feb 17, 2020
Jason Lee, Dustin Tran, Orhan Firat, Kyunghyun Cho


  Access Paper or Ask Questions