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 Graham Neubig

Graham Neubig

Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations


Dec 17, 2021
Siddhant Arora, Danish Pruthi, Norman Sadeh, William W. Cohen, Zachary C. Lipton, Graham Neubig

Figure 1 for Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations
Figure 2 for Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations
Figure 3 for Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations
Figure 4 for Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations
* AAAI 2022 
  Access Paper or Ask Questions

VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning


Dec 05, 2021
Qibin Chen, Jeremy Lacomis, Edward J. Schwartz, Graham Neubig, Bogdan Vasilescu, Claire Le Goues

Figure 1 for VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning
Figure 2 for VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning
Figure 3 for VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning
Figure 4 for VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning
* Accepted by ICSE 2022 
  Access Paper or Ask Questions

DEEP: DEnoising Entity Pre-training for Neural Machine Translation


Nov 14, 2021
Junjie Hu, Hiroaki Hayashi, Kyunghyun Cho, Graham Neubig

Figure 1 for DEEP: DEnoising Entity Pre-training for Neural Machine Translation
Figure 2 for DEEP: DEnoising Entity Pre-training for Neural Machine Translation
Figure 3 for DEEP: DEnoising Entity Pre-training for Neural Machine Translation
Figure 4 for DEEP: DEnoising Entity Pre-training for Neural Machine Translation
* 13 pages 
  Access Paper or Ask Questions

Lexically Aware Semi-Supervised Learning for OCR Post-Correction


Nov 04, 2021
Shruti Rijhwani, Daisy Rosenblum, Antonios Anastasopoulos, Graham Neubig

Figure 1 for Lexically Aware Semi-Supervised Learning for OCR Post-Correction
Figure 2 for Lexically Aware Semi-Supervised Learning for OCR Post-Correction
Figure 3 for Lexically Aware Semi-Supervised Learning for OCR Post-Correction
Figure 4 for Lexically Aware Semi-Supervised Learning for OCR Post-Correction
* Accepted to the Transactions of the Association for Computational Linguistics (TACL) 
  Access Paper or Ask Questions

On The Ingredients of an Effective Zero-shot Semantic Parser


Oct 15, 2021
Pengcheng Yin, John Wieting, Avirup Sil, Graham Neubig

Figure 1 for On The Ingredients of an Effective Zero-shot Semantic Parser
Figure 2 for On The Ingredients of an Effective Zero-shot Semantic Parser
Figure 3 for On The Ingredients of an Effective Zero-shot Semantic Parser
Figure 4 for On The Ingredients of an Effective Zero-shot Semantic Parser

  Access Paper or Ask Questions

Breaking Down Multilingual Machine Translation


Oct 15, 2021
Ting-Rui Chiang, Yi-Pei Chen, Yi-Ting Yeh, Graham Neubig

Figure 1 for Breaking Down Multilingual Machine Translation
Figure 2 for Breaking Down Multilingual Machine Translation
Figure 3 for Breaking Down Multilingual Machine Translation
Figure 4 for Breaking Down Multilingual Machine Translation

  Access Paper or Ask Questions

Systematic Inequalities in Language Technology Performance across the World's Languages


Oct 13, 2021
Damián Blasi, Antonios Anastasopoulos, Graham Neubig

Figure 1 for Systematic Inequalities in Language Technology Performance across the World's Languages
Figure 2 for Systematic Inequalities in Language Technology Performance across the World's Languages
Figure 3 for Systematic Inequalities in Language Technology Performance across the World's Languages
Figure 4 for Systematic Inequalities in Language Technology Performance across the World's Languages

  Access Paper or Ask Questions

Towards a Unified View of Parameter-Efficient Transfer Learning


Oct 08, 2021
Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, Graham Neubig

Figure 1 for Towards a Unified View of Parameter-Efficient Transfer Learning
Figure 2 for Towards a Unified View of Parameter-Efficient Transfer Learning
Figure 3 for Towards a Unified View of Parameter-Efficient Transfer Learning
Figure 4 for Towards a Unified View of Parameter-Efficient Transfer Learning
* under review 
  Access Paper or Ask Questions

Capturing Structural Locality in Non-parametric Language Models


Oct 06, 2021
Frank F. Xu, Junxian He, Graham Neubig, Vincent J. Hellendoorn

Figure 1 for Capturing Structural Locality in Non-parametric Language Models
Figure 2 for Capturing Structural Locality in Non-parametric Language Models
Figure 3 for Capturing Structural Locality in Non-parametric Language Models
Figure 4 for Capturing Structural Locality in Non-parametric Language Models

  Access Paper or Ask Questions

Learning to Superoptimize Real-world Programs


Sep 28, 2021
Alex Shypula, Pengcheng Yin, Jeremy Lacomis, Claire Le Goues, Edward Schwartz, Graham Neubig

Figure 1 for Learning to Superoptimize Real-world Programs
Figure 2 for Learning to Superoptimize Real-world Programs
Figure 3 for Learning to Superoptimize Real-world Programs
Figure 4 for Learning to Superoptimize Real-world Programs
* 10 pages, 6 figures, under review at the Thirty-Sixth AAAI Conference on Artificial Intelligence 
  Access Paper or Ask Questions

Dependency Induction Through the Lens of Visual Perception


Sep 20, 2021
Ruisi Su, Shruti Rijhwani, Hao Zhu, Junxian He, Xinyu Wang, Yonatan Bisk, Graham Neubig

Figure 1 for Dependency Induction Through the Lens of Visual Perception
Figure 2 for Dependency Induction Through the Lens of Visual Perception
Figure 3 for Dependency Induction Through the Lens of Visual Perception
Figure 4 for Dependency Induction Through the Lens of Visual Perception
* Accepted to CoNLL 2021 
  Access Paper or Ask Questions

Hierarchical Control of Situated Agents through Natural Language


Sep 16, 2021
Shuyan Zhou, Pengcheng Yin, Graham Neubig

Figure 1 for Hierarchical Control of Situated Agents through Natural Language
Figure 2 for Hierarchical Control of Situated Agents through Natural Language
Figure 3 for Hierarchical Control of Situated Agents through Natural Language
Figure 4 for Hierarchical Control of Situated Agents through Natural Language

  Access Paper or Ask Questions

When Does Translation Require Context? A Data-driven, Multilingual Exploration


Sep 15, 2021
Kayo Yin, Patrick Fernandes, André F. T. Martins, Graham Neubig

Figure 1 for When Does Translation Require Context? A Data-driven, Multilingual Exploration
Figure 2 for When Does Translation Require Context? A Data-driven, Multilingual Exploration
Figure 3 for When Does Translation Require Context? A Data-driven, Multilingual Exploration
Figure 4 for When Does Translation Require Context? A Data-driven, Multilingual Exploration

  Access Paper or Ask Questions

Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative


Sep 15, 2021
Lucio M. Dery, Paul Michel, Ameet Talwalkar, Graham Neubig

Figure 1 for Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
Figure 2 for Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
Figure 3 for Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
Figure 4 for Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative
* 16 pages, 4 figures 
  Access Paper or Ask Questions

When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection


Sep 13, 2021
Aditi Chaudhary, Kayo Yin, Antonios Anastasopoulos, Graham Neubig

Figure 1 for When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection
Figure 2 for When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection
Figure 3 for When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection
Figure 4 for When is Wall a Pared and when a Muro? -- Extracting Rules Governing Lexical Selection
* Accepted at EMNLP 2021 
  Access Paper or Ask Questions

Efficient Test Time Adapter Ensembling for Low-resource Language Varieties


Sep 10, 2021
Xinyi Wang, Yulia Tsvetkov, Sebastian Ruder, Graham Neubig

Figure 1 for Efficient Test Time Adapter Ensembling for Low-resource Language Varieties
Figure 2 for Efficient Test Time Adapter Ensembling for Low-resource Language Varieties
Figure 3 for Efficient Test Time Adapter Ensembling for Low-resource Language Varieties
Figure 4 for Efficient Test Time Adapter Ensembling for Low-resource Language Varieties
* EMNLP 2021 Findings 
  Access Paper or Ask Questions

AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages


Sep 10, 2021
Machel Reid, Junjie Hu, Graham Neubig, Yutaka Matsuo

Figure 1 for AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages
Figure 2 for AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages
Figure 3 for AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages
Figure 4 for AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African Languages
* EMNLP 2021 
  Access Paper or Ask Questions

Efficient Nearest Neighbor Language Models


Sep 09, 2021
Junxian He, Graham Neubig, Taylor Berg-Kirkpatrick

Figure 1 for Efficient Nearest Neighbor Language Models
Figure 2 for Efficient Nearest Neighbor Language Models
Figure 3 for Efficient Nearest Neighbor Language Models
Figure 4 for Efficient Nearest Neighbor Language Models
* EMNLP 2021 
  Access Paper or Ask Questions

Distributionally Robust Multilingual Machine Translation


Sep 09, 2021
Chunting Zhou, Daniel Levy, Xian Li, Marjan Ghazvininejad, Graham Neubig

Figure 1 for Distributionally Robust Multilingual Machine Translation
Figure 2 for Distributionally Robust Multilingual Machine Translation
Figure 3 for Distributionally Robust Multilingual Machine Translation
Figure 4 for Distributionally Robust Multilingual Machine Translation
* Long paper accepted by EMNLP2021 main conference 
  Access Paper or Ask Questions

Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing


Jul 28, 2021
Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, Graham Neubig

Figure 1 for Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
Figure 2 for Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
Figure 3 for Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
Figure 4 for Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
* Website: http://pretrain.nlpedia.ai/ 
  Access Paper or Ask Questions

Few-shot Language Coordination by Modeling Theory of Mind


Jul 12, 2021
Hao Zhu, Graham Neubig, Yonatan Bisk

Figure 1 for Few-shot Language Coordination by Modeling Theory of Mind
Figure 2 for Few-shot Language Coordination by Modeling Theory of Mind
Figure 3 for Few-shot Language Coordination by Modeling Theory of Mind
Figure 4 for Few-shot Language Coordination by Modeling Theory of Mind
* Thirty-eighth International Conference on Machine Learning (ICML 2021) 
  Access Paper or Ask Questions

BARTScore: Evaluating Generated Text as Text Generation


Jun 22, 2021
Weizhe Yuan, Graham Neubig, Pengfei Liu

Figure 1 for BARTScore: Evaluating Generated Text as Text Generation
Figure 2 for BARTScore: Evaluating Generated Text as Text Generation
Figure 3 for BARTScore: Evaluating Generated Text as Text Generation
Figure 4 for BARTScore: Evaluating Generated Text as Text Generation
* Demo at http://explainaboard.nlpedia.ai/leaderboard/task-meval/ 
  Access Paper or Ask Questions

Phrase-level Active Learning for Neural Machine Translation


Jun 21, 2021
Junjie Hu, Graham Neubig

Figure 1 for Phrase-level Active Learning for Neural Machine Translation
Figure 2 for Phrase-level Active Learning for Neural Machine Translation
Figure 3 for Phrase-level Active Learning for Neural Machine Translation
Figure 4 for Phrase-level Active Learning for Neural Machine Translation

  Access Paper or Ask Questions

Examining and Combating Spurious Features under Distribution Shift


Jun 14, 2021
Chunting Zhou, Xuezhe Ma, Paul Michel, Graham Neubig

Figure 1 for Examining and Combating Spurious Features under Distribution Shift
Figure 2 for Examining and Combating Spurious Features under Distribution Shift
Figure 3 for Examining and Combating Spurious Features under Distribution Shift
Figure 4 for Examining and Combating Spurious Features under Distribution Shift
* Accepted by ICML2021 
  Access Paper or Ask Questions

CitationIE: Leveraging the Citation Graph for Scientific Information Extraction


Jun 03, 2021
Vijay Viswanathan, Graham Neubig, Pengfei Liu

Figure 1 for CitationIE: Leveraging the Citation Graph for Scientific Information Extraction
Figure 2 for CitationIE: Leveraging the Citation Graph for Scientific Information Extraction
Figure 3 for CitationIE: Leveraging the Citation Graph for Scientific Information Extraction
Figure 4 for CitationIE: Leveraging the Citation Graph for Scientific Information Extraction
* ACL-IJCNLP 2021 camera-ready (long paper in main conference) 
  Access Paper or Ask Questions

Measuring and Increasing Context Usage in Context-Aware Machine Translation


Jun 02, 2021
Patrick Fernandes, Kayo Yin, Graham Neubig, André F. T. Martins

Figure 1 for Measuring and Increasing Context Usage in Context-Aware Machine Translation
Figure 2 for Measuring and Increasing Context Usage in Context-Aware Machine Translation
Figure 3 for Measuring and Increasing Context Usage in Context-Aware Machine Translation
Figure 4 for Measuring and Increasing Context Usage in Context-Aware Machine Translation
* ACL 2021 
  Access Paper or Ask Questions

Do Context-Aware Translation Models Pay the Right Attention?


May 21, 2021
Kayo Yin, Patrick Fernandes, Danish Pruthi, Aditi Chaudhary, André F. T. Martins, Graham Neubig

Figure 1 for Do Context-Aware Translation Models Pay the Right Attention?
Figure 2 for Do Context-Aware Translation Models Pay the Right Attention?
Figure 3 for Do Context-Aware Translation Models Pay the Right Attention?
Figure 4 for Do Context-Aware Translation Models Pay the Right Attention?
* Accepted to ACL 2021 
  Access Paper or Ask Questions

Data Augmentation for Sign Language Gloss Translation


May 16, 2021
Amit Moryossef, Kayo Yin, Graham Neubig, Yoav Goldberg

Figure 1 for Data Augmentation for Sign Language Gloss Translation
Figure 2 for Data Augmentation for Sign Language Gloss Translation
Figure 3 for Data Augmentation for Sign Language Gloss Translation
Figure 4 for Data Augmentation for Sign Language Gloss Translation
* 4 pages, 1 page abstract 
  Access Paper or Ask Questions