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 Yonatan Belinkov

Natural Language Inference with a Human Touch: Using Human Explanations to Guide Model Attention


Apr 16, 2021
Joe Stacey, Yonatan Belinkov, Marek Rei


  Access Paper or Ask Questions

Probing Classifiers: Promises, Shortcomings, and Alternatives


Mar 04, 2021
Yonatan Belinkov

* Updated version, under review in Computational Linguistics 

  Access Paper or Ask Questions

Learning from others' mistakes: Avoiding dataset biases without modeling them


Dec 02, 2020
Victor Sanh, Thomas Wolf, Yonatan Belinkov, Alexander M. Rush

* 15 pages, 6 figures, 6 tables 

  Access Paper or Ask Questions

Similarity Analysis of Self-Supervised Speech Representations


Oct 22, 2020
Yu-An Chung, Yonatan Belinkov, James Glass


  Access Paper or Ask Questions

Analyzing Individual Neurons in Pre-trained Language Models


Oct 06, 2020
Nadir Durrani, Hassan Sajjad, Fahim Dalvi, Yonatan Belinkov

* Accepted in EMNLP 2020 

  Access Paper or Ask Questions

Probing Neural Dialog Models for Conversational Understanding


Jun 07, 2020
Abdelrhman Saleh, Tovly Deutsch, Stephen Casper, Yonatan Belinkov, Stuart Shieber


  Access Paper or Ask Questions

The Sensitivity of Language Models and Humans to Winograd Schema Perturbations


May 07, 2020
Mostafa Abdou, Vinit Ravishankar, Maria Barrett, Yonatan Belinkov, Desmond Elliott, Anders Søgaard

* ACL 2020 

  Access Paper or Ask Questions

Similarity Analysis of Contextual Word Representation Models


May 03, 2020
John M. Wu, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, James Glass

* Accepted to ACL 2020 

  Access Paper or Ask Questions

Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance?


May 02, 2020
Abhilasha Ravichander, Yonatan Belinkov, Eduard Hovy


  Access Paper or Ask Questions

Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias


Apr 26, 2020
Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Yaron Singer, Stuart Shieber


  Access Paper or Ask Questions

Exploiting Redundancy in Pre-trained Language Models for Efficient Transfer Learning


Apr 08, 2020
Fahim Dalvi, Hassan Sajjad, Nadir Durrani, Yonatan Belinkov

* 11 Pages, 5 figures 

  Access Paper or Ask Questions

Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages


Nov 08, 2019
Mirac Suzgun, Sebastian Gehrmann, Yonatan Belinkov, Stuart M. Shieber


  Access Paper or Ask Questions

On the Linguistic Representational Power of Neural Machine Translation Models


Nov 01, 2019
Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Hassan Sajjad, James Glass

* Accepted to appear in the Journal of Computational Linguistics 

  Access Paper or Ask Questions

A Constructive Prediction of the Generalization Error Across Scales


Sep 27, 2019
Jonathan S. Rosenfeld, Amir Rosenfeld, Yonatan Belinkov, Nir Shavit


  Access Paper or Ask Questions

On Adversarial Removal of Hypothesis-only Bias in Natural Language Inference


Jul 09, 2019
Yonatan Belinkov, Adam Poliak, Stuart M. Shieber, Benjamin Van Durme, Alexander M. Rush

* StarSem 2019 - The Eighth Joint Conference on Lexical and Computational Semantics 

  Access Paper or Ask Questions

Don't Take the Premise for Granted: Mitigating Artifacts in Natural Language Inference


Jul 09, 2019
Yonatan Belinkov, Adam Poliak, Stuart M. Shieber, Benjamin Van Durme, Alexander M. Rush

* ACL 2019 

  Access Paper or Ask Questions

Analyzing Phonetic and Graphemic Representations in End-to-End Automatic Speech Recognition


Jul 09, 2019
Yonatan Belinkov, Ahmed Ali, James Glass

* Interspeech 2019 (slightly expanded version) 

  Access Paper or Ask Questions

Findings of the First Shared Task on Machine Translation Robustness


Jul 03, 2019
Xian Li, Paul Michel, Antonios Anastasopoulos, Yonatan Belinkov, Nadir Durrani, Orhan Firat, Philipp Koehn, Graham Neubig, Juan Pino, Hassan Sajjad


  Access Paper or Ask Questions

Adversarial Regularization for Visual Question Answering: Strengths, Shortcomings, and Side Effects


Jun 20, 2019
Gabriel Grand, Yonatan Belinkov

* In Proceedings of the 2nd Workshop on Shortcomings in Vision and Language (SiVL) at NAACL-HLT 2019 

  Access Paper or Ask Questions

Analyzing the Structure of Attention in a Transformer Language Model


Jun 18, 2019
Jesse Vig, Yonatan Belinkov

* To appear in ACL BlackboxNLP workshop 

  Access Paper or Ask Questions

LSTM Networks Can Perform Dynamic Counting


Jun 09, 2019
Mirac Suzgun, Sebastian Gehrmann, Yonatan Belinkov, Stuart M. Shieber

* ACL 2019 Workshop on Deep Learning and Formal Languages 

  Access Paper or Ask Questions

Improving Neural Language Models by Segmenting, Attending, and Predicting the Future


Jun 04, 2019
Hongyin Luo, Lan Jiang, Yonatan Belinkov, James Glass

* Accepted by ACL 2019 

  Access Paper or Ask Questions

Linguistic Knowledge and Transferability of Contextual Representations


Apr 11, 2019
Nelson F. Liu, Matt Gardner, Yonatan Belinkov, Matthew E. Peters, Noah A. Smith

* 22 pages, 4 figures; to appear at NAACL 2019. Converted appendices to two-column format for camera-ready 

  Access Paper or Ask Questions

Character-based Surprisal as a Model of Human Reading in the Presence of Errors


Feb 02, 2019
Michael Hahn, Frank Keller, Yonatan Bisk, Yonatan Belinkov

* Under double-blind peer review, please do not disseminate widely 

  Access Paper or Ask Questions

Analysis Methods in Neural Language Processing: A Survey


Jan 14, 2019
Yonatan Belinkov, James Glass

* Version including the supplementary materials (3 tables), also available at https://boknilev.github.io/nlp-analysis-methods 

  Access Paper or Ask Questions

NeuroX: A Toolkit for Analyzing Individual Neurons in Neural Networks


Dec 21, 2018
Fahim Dalvi, Avery Nortonsmith, D. Anthony Bau, Yonatan Belinkov, Hassan Sajjad, Nadir Durrani, James Glass

* AAAI Conference on Artificial Intelligence (AAAI 2019), Demonstration track, pages 2 

  Access Paper or Ask Questions

What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models


Dec 21, 2018
Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Yonatan Belinkov, Anthony Bau, James Glass

* AAA 2019, pages 10, AAAI Conference on Artificial Intelligence (AAAI 2019) 

  Access Paper or Ask Questions