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

Measuring and Increasing Context Usage in Context-Aware Machine Translation


May 07, 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

Paraphrastic Representations at Scale


Apr 30, 2021
John Wieting, Kevin Gimpel, Graham Neubig, Taylor Berg-Kirkpatrick

Figure 1 for Paraphrastic Representations at Scale
Figure 2 for Paraphrastic Representations at Scale
Figure 3 for Paraphrastic Representations at Scale
Figure 4 for Paraphrastic Representations at Scale

  Access Paper or Ask Questions

AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages


Apr 18, 2021
Abteen Ebrahimi, Manuel Mager, Arturo Oncevay, Vishrav Chaudhary, Luis Chiruzzo, Angela Fan, John Ortega, Ricardo Ramos, Annette Rios, Ivan Vladimir, Gustavo A. Giménez-Lugo, Elisabeth Mager, Graham Neubig, Alexis Palmer, Rolando A. Coto Solano, Ngoc Thang Vu, Katharina Kann

Figure 1 for AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Figure 2 for AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Figure 3 for AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Figure 4 for AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages

  Access Paper or Ask Questions

MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning


Apr 16, 2021
Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Hassan Awadallah

Figure 1 for MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Figure 2 for MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Figure 3 for MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Figure 4 for MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
* 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021) 
  Access Paper or Ask Questions

XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation


Apr 15, 2021
Sebastian Ruder, Noah Constant, Jan Botha, Aditya Siddhant, Orhan Firat, Jinlan Fu, Pengfei Liu, Junjie Hu, Graham Neubig, Melvin Johnson

Figure 1 for XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation
Figure 2 for XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation
Figure 3 for XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation
Figure 4 for XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation

  Access Paper or Ask Questions

Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models


Apr 15, 2021
Po-Yao Huang, Mandela Patrick, Junjie Hu, Graham Neubig, Florian Metze, Alexander Hauptmann

Figure 1 for Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models
Figure 2 for Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models
Figure 3 for Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models
Figure 4 for Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models
* accepted by NAACL 2021 
  Access Paper or Ask Questions

EXPLAINABOARD: An Explainable Leaderboard for NLP


Apr 13, 2021
Pengfei Liu, Jinlan Fu, Yang Xiao, Weizhe Yuan, Shuaicheng Chang, Junqi Dai, Yixin Liu, Zihuiwen Ye, Graham Neubig

Figure 1 for EXPLAINABOARD: An Explainable Leaderboard for NLP
Figure 2 for EXPLAINABOARD: An Explainable Leaderboard for NLP
Figure 3 for EXPLAINABOARD: An Explainable Leaderboard for NLP
Figure 4 for EXPLAINABOARD: An Explainable Leaderboard for NLP

  Access Paper or Ask Questions

Multi-view Subword Regularization


Apr 06, 2021
Xinyi Wang, Sebastian Ruder, Graham Neubig

Figure 1 for Multi-view Subword Regularization
Figure 2 for Multi-view Subword Regularization
Figure 3 for Multi-view Subword Regularization
Figure 4 for Multi-view Subword Regularization
* Accepted at NAACL 2021 
  Access Paper or Ask Questions

Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties


Apr 04, 2021
Kathleen Siminyu, Xinjian Li, Antonios Anastasopoulos, David Mortensen, Michael R. Marlo, Graham Neubig

Figure 1 for Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Figure 2 for Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Figure 3 for Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties
Figure 4 for Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties

  Access Paper or Ask Questions

Modeling the Second Player in Distributionally Robust Optimization


Mar 31, 2021
Paul Michel, Tatsunori Hashimoto, Graham Neubig

Figure 1 for Modeling the Second Player in Distributionally Robust Optimization
Figure 2 for Modeling the Second Player in Distributionally Robust Optimization
Figure 3 for Modeling the Second Player in Distributionally Robust Optimization
Figure 4 for Modeling the Second Player in Distributionally Robust Optimization
* Accepted at ICLR 2021 
  Access Paper or Ask Questions

Evaluating the Morphosyntactic Well-formedness of Generated Texts


Mar 30, 2021
Adithya Pratapa, Antonios Anastasopoulos, Shruti Rijhwani, Aditi Chaudhary, David R. Mortensen, Graham Neubig, Yulia Tsvetkov

Figure 1 for Evaluating the Morphosyntactic Well-formedness of Generated Texts
Figure 2 for Evaluating the Morphosyntactic Well-formedness of Generated Texts
Figure 3 for Evaluating the Morphosyntactic Well-formedness of Generated Texts
Figure 4 for Evaluating the Morphosyntactic Well-formedness of Generated Texts

  Access Paper or Ask Questions

MasakhaNER: Named Entity Recognition for African Languages


Mar 22, 2021
David Ifeoluwa Adelani, Jade Abbott, Graham Neubig, Daniel D'souza, Julia Kreutzer, Constantine Lignos, Chester Palen-Michel, Happy Buzaaba, Shruti Rijhwani, Sebastian Ruder, Stephen Mayhew, Israel Abebe Azime, Shamsuddeen Muhammad, Chris Chinenye Emezue, Joyce Nakatumba-Nabende, Perez Ogayo, Anuoluwapo Aremu, Catherine Gitau, Derguene Mbaye, Jesujoba Alabi, Seid Muhie Yimam, Tajuddeen Gwadabe, Ignatius Ezeani, Rubungo Andre Niyongabo, Jonathan Mukiibi, Verrah Otiende, Iroro Orife, Davis David, Samba Ngom, Tosin Adewumi, Paul Rayson, Mofetoluwa Adeyemi, Gerald Muriuki, Emmanuel Anebi, Chiamaka Chukwuneke, Nkiruka Odu, Eric Peter Wairagala, Samuel Oyerinde, Clemencia Siro, Tobius Saul Bateesa, Temilola Oloyede, Yvonne Wambui, Victor Akinode, Deborah Nabagereka, Maurice Katusiime, Ayodele Awokoya, Mouhamadane MBOUP, Dibora Gebreyohannes, Henok Tilaye, Kelechi Nwaike, Degaga Wolde, Abdoulaye Faye, Blessing Sibanda, Orevaoghene Ahia, Bonaventure F. P. Dossou, Kelechi Ogueji, Thierno Ibrahima DIOP, Abdoulaye Diallo, Adewale Akinfaderin, Tendai Marengereke, Salomey Osei

Figure 1 for MasakhaNER: Named Entity Recognition for African Languages
Figure 2 for MasakhaNER: Named Entity Recognition for African Languages
Figure 3 for MasakhaNER: Named Entity Recognition for African Languages
Figure 4 for MasakhaNER: Named Entity Recognition for African Languages
* Accepted at the AfricaNLP Workshop @EACL 2021 
  Access Paper or Ask Questions

Meta Back-translation


Feb 15, 2021
Hieu Pham, Xinyi Wang, Yiming Yang, Graham Neubig

Figure 1 for Meta Back-translation
Figure 2 for Meta Back-translation
Figure 3 for Meta Back-translation
Figure 4 for Meta Back-translation
* Accepted to ICLR 2021 
  Access Paper or Ask Questions

Towards More Fine-grained and Reliable NLP Performance Prediction


Feb 10, 2021
Zihuiwen Ye, Pengfei Liu, Jinlan Fu, Graham Neubig

Figure 1 for Towards More Fine-grained and Reliable NLP Performance Prediction
Figure 2 for Towards More Fine-grained and Reliable NLP Performance Prediction
Figure 3 for Towards More Fine-grained and Reliable NLP Performance Prediction
Figure 4 for Towards More Fine-grained and Reliable NLP Performance Prediction
* Accepted by EACL 2021 
  Access Paper or Ask Questions

Can We Automate Scientific Reviewing?


Jan 30, 2021
Weizhe Yuan, Pengfei Liu, Graham Neubig

Figure 1 for Can We Automate Scientific Reviewing?
Figure 2 for Can We Automate Scientific Reviewing?
Figure 3 for Can We Automate Scientific Reviewing?
Figure 4 for Can We Automate Scientific Reviewing?
* TLDR: This paper proposes to use NLP models to generate first-pass peer reviews for scientific papers . (Generated by our system.) 
  Access Paper or Ask Questions

Learning Structural Edits via Incremental Tree Transformations


Jan 28, 2021
Ziyu Yao, Frank F. Xu, Pengcheng Yin, Huan Sun, Graham Neubig

Figure 1 for Learning Structural Edits via Incremental Tree Transformations
Figure 2 for Learning Structural Edits via Incremental Tree Transformations
Figure 3 for Learning Structural Edits via Incremental Tree Transformations
Figure 4 for Learning Structural Edits via Incremental Tree Transformations
* ICLR 2021 
  Access Paper or Ask Questions

Word Alignment by Fine-tuning Embeddings on Parallel Corpora


Jan 24, 2021
Zi-Yi Dou, Graham Neubig

Figure 1 for Word Alignment by Fine-tuning Embeddings on Parallel Corpora
Figure 2 for Word Alignment by Fine-tuning Embeddings on Parallel Corpora
Figure 3 for Word Alignment by Fine-tuning Embeddings on Parallel Corpora
Figure 4 for Word Alignment by Fine-tuning Embeddings on Parallel Corpora
* EACL 2021 
  Access Paper or Ask Questions

Interpretable Multi-dataset Evaluation for Named Entity Recognition


Dec 09, 2020
Jinlan Fu, Pengfei Liu, Graham Neubig

Figure 1 for Interpretable Multi-dataset Evaluation for Named Entity Recognition
Figure 2 for Interpretable Multi-dataset Evaluation for Named Entity Recognition
Figure 3 for Interpretable Multi-dataset Evaluation for Named Entity Recognition
Figure 4 for Interpretable Multi-dataset Evaluation for Named Entity Recognition
* Accepted by EMNLP 2020 
  Access Paper or Ask Questions

How Can We Know When Language Models Know?


Dec 02, 2020
Zhengbao Jiang, Jun Araki, Haibo Ding, Graham Neubig


  Access Paper or Ask Questions

Evaluating Explanations: How much do explanations from the teacher aid students?


Dec 01, 2020
Danish Pruthi, Bhuwan Dhingra, Livio Baldini Soares, Michael Collins, Zachary C. Lipton, Graham Neubig, William W. Cohen

Figure 1 for Evaluating Explanations: How much do explanations from the teacher aid students?
Figure 2 for Evaluating Explanations: How much do explanations from the teacher aid students?
Figure 3 for Evaluating Explanations: How much do explanations from the teacher aid students?
Figure 4 for Evaluating Explanations: How much do explanations from the teacher aid students?
* Preprint 
  Access Paper or Ask Questions

Decoding and Diversity in Machine Translation


Nov 26, 2020
Nicholas Roberts, Davis Liang, Graham Neubig, Zachary C. Lipton

Figure 1 for Decoding and Diversity in Machine Translation
Figure 2 for Decoding and Diversity in Machine Translation
Figure 3 for Decoding and Diversity in Machine Translation
Figure 4 for Decoding and Diversity in Machine Translation
* Presented at the Resistance AI Workshop, 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada 
  Access Paper or Ask Questions

WikiAsp: A Dataset for Multi-domain Aspect-based Summarization


Nov 16, 2020
Hiroaki Hayashi, Prashant Budania, Peng Wang, Chris Ackerson, Raj Neervannan, Graham Neubig

Figure 1 for WikiAsp: A Dataset for Multi-domain Aspect-based Summarization
Figure 2 for WikiAsp: A Dataset for Multi-domain Aspect-based Summarization
Figure 3 for WikiAsp: A Dataset for Multi-domain Aspect-based Summarization
Figure 4 for WikiAsp: A Dataset for Multi-domain Aspect-based Summarization
* Transaction of the ACL 
  Access Paper or Ask Questions

OCR Post Correction for Endangered Language Texts


Nov 10, 2020
Shruti Rijhwani, Antonios Anastasopoulos, Graham Neubig

Figure 1 for OCR Post Correction for Endangered Language Texts
Figure 2 for OCR Post Correction for Endangered Language Texts
Figure 3 for OCR Post Correction for Endangered Language Texts
Figure 4 for OCR Post Correction for Endangered Language Texts
* Accepted to EMNLP 2020 
  Access Paper or Ask Questions

Weakly- and Semi-supervised Evidence Extraction


Nov 03, 2020
Danish Pruthi, Bhuwan Dhingra, Graham Neubig, Zachary C. Lipton

Figure 1 for Weakly- and Semi-supervised Evidence Extraction
Figure 2 for Weakly- and Semi-supervised Evidence Extraction
Figure 3 for Weakly- and Semi-supervised Evidence Extraction
Figure 4 for Weakly- and Semi-supervised Evidence Extraction
* Accepted to the Findings of EMNLP 2020, to be presented at BlackBoxNLP 
  Access Paper or Ask Questions

Reducing Confusion in Active Learning for Part-Of-Speech Tagging


Nov 02, 2020
Aditi Chaudhary, Antonios Anastasopoulos, Zaid Sheikh, Graham Neubig

Figure 1 for Reducing Confusion in Active Learning for Part-Of-Speech Tagging
Figure 2 for Reducing Confusion in Active Learning for Part-Of-Speech Tagging
Figure 3 for Reducing Confusion in Active Learning for Part-Of-Speech Tagging
Figure 4 for Reducing Confusion in Active Learning for Part-Of-Speech Tagging
* To appear in TACL 2020. This is a pre-MIT Press publication version 
  Access Paper or Ask Questions