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 Roy Schwartz

Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand?


Apr 22, 2021
William Merrill, Yoav Goldberg, Roy Schwartz, Noah A. Smith

* Accepted at TACL; pre-MIT Press publication version 

  Access Paper or Ask Questions

Random Feature Attention


Mar 19, 2021
Hao Peng, Nikolaos Pappas, Dani Yogatama, Roy Schwartz, Noah A. Smith, Lingpeng Kong

* ICLR 2021 

  Access Paper or Ask Questions

Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA


Mar 17, 2021
Yonatan Bitton, Gabriel Stanovsky, Roy Schwartz, Michael Elhadad

* Accepted to NAACL 2021 

  Access Paper or Ask Questions

Parameter Norm Growth During Training of Transformers


Nov 11, 2020
William Merrill, Vivek Ramanujan, Yoav Goldberg, Roy Schwartz, Noah Smith

* Preprint. 9 body pages with appendix 

  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

* Proceedings of EMNLP 2020 

  Access Paper or Ask Questions

Extracting a Knowledge Base of Mechanisms from COVID-19 Papers


Oct 08, 2020
Aida Amini, Tom Hope, David Wadden, Madeleine van Zuylen, Eric Horvitz, Roy Schwartz, Hannaneh Hajishirzi

* Tom Hope and Aida Amini made an equal contribution as joint first authors, listed in alphabetical order. Data and code: https://git.io/JUhv7 

  Access Paper or Ask Questions

A Mixture of $h-1$ Heads is Better than $h$ Heads


May 13, 2020
Hao Peng, Roy Schwartz, Dianqi Li, Noah A. Smith

* ACL2020 

  Access Paper or Ask Questions

The Right Tool for the Job: Matching Model and Instance Complexities


May 09, 2020
Roy Schwartz, Gabriel Stanovsky, Swabha Swayamdipta, Jesse Dodge, Noah A. Smith

* ACL 2020; 12 pages; code available in https://github.com/allenai/sledgehammer 

  Access Paper or Ask Questions

A Formal Hierarchy of RNN Architectures


Apr 24, 2020
William Merrill, Gail Weiss, Yoav Goldberg, Roy Schwartz, Noah A. Smith, Eran Yahav

* To appear at ACL 2020. Updated to include computational cost estimates 

  Access Paper or Ask Questions

Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping


Feb 15, 2020
Jesse Dodge, Gabriel Ilharco, Roy Schwartz, Ali Farhadi, Hannaneh Hajishirzi, Noah Smith


  Access Paper or Ask Questions

Fair Correlation Clustering


Feb 10, 2020
Saba Ahmadi, Sainyam Galhotra, Barna Saha, Roy Schwartz


  Access Paper or Ask Questions

Knowledge Enhanced Contextual Word Representations


Sep 09, 2019
Matthew E. Peters, Mark Neumann, Robert L. Logan IV, Roy Schwartz, Vidur Joshi, Sameer Singh, Noah A. Smith

* EMNLP 2019 

  Access Paper or Ask Questions

RNN Architecture Learning with Sparse Regularization


Sep 06, 2019
Jesse Dodge, Roy Schwartz, Hao Peng, Noah A. Smith


  Access Paper or Ask Questions

Show Your Work: Improved Reporting of Experimental Results


Sep 06, 2019
Jesse Dodge, Suchin Gururangan, Dallas Card, Roy Schwartz, Noah A. Smith


  Access Paper or Ask Questions

PaLM: A Hybrid Parser and Language Model


Sep 04, 2019
Hao Peng, Roy Schwartz, Noah A. Smith

* EMNLP 2019 short paper 

  Access Paper or Ask Questions

Green AI


Aug 13, 2019
Roy Schwartz, Jesse Dodge, Noah A. Smith, Oren Etzioni

* 12 pages 

  Access Paper or Ask Questions

Inoculation by Fine-Tuning: A Method for Analyzing Challenge Datasets


Apr 26, 2019
Nelson F. Liu, Roy Schwartz, Noah A. Smith

* 9 pages, 4 figures; to appear at NAACL 2019 

  Access Paper or Ask Questions

Rational Recurrences


Aug 28, 2018
Hao Peng, Roy Schwartz, Sam Thomson, Noah A. Smith

* EMNLP 2018 

  Access Paper or Ask Questions

SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference


Aug 16, 2018
Rowan Zellers, Yonatan Bisk, Roy Schwartz, Yejin Choi

* EMNLP 2018 

  Access Paper or Ask Questions

LSTMs Exploit Linguistic Attributes of Data


May 29, 2018
Nelson F. Liu, Omer Levy, Roy Schwartz, Chenhao Tan, Noah A. Smith

* 7 pages, 4 figures; accepted to ACL 2018 RepL4NLP workshop 

  Access Paper or Ask Questions

SoPa: Bridging CNNs, RNNs, and Weighted Finite-State Machines


May 15, 2018
Roy Schwartz, Sam Thomson, Noah A. Smith

* ACL 2018, 12 pages. Code available at https://github.com/Noahs-ARK/soft_patterns 

  Access Paper or Ask Questions

A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications


Apr 25, 2018
Dongyeop Kang, Waleed Ammar, Bhavana Dalvi, Madeleine van Zuylen, Sebastian Kohlmeier, Eduard Hovy, Roy Schwartz

* NAACL 2018 

  Access Paper or Ask Questions

Annotation Artifacts in Natural Language Inference Data


Apr 16, 2018
Suchin Gururangan, Swabha Swayamdipta, Omer Levy, Roy Schwartz, Samuel R. Bowman, Noah A. Smith

* 6 pages, 1 figure, NAACL 2018 

  Access Paper or Ask Questions