Alert button
Picture for Michael Collins

Michael Collins

Alert button

Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model

Oct 05, 2022
Jacob Eisenstein, Daniel Andor, Bernd Bohnet, Michael Collins, David Mimno

Figure 1 for Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model
Figure 2 for Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model
Figure 3 for Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model
Figure 4 for Honest Students from Untrusted Teachers: Learning an Interpretable Question-Answering Pipeline from a Pretrained Language Model
Viaarxiv icon

A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation

Mar 28, 2022
Shashi Narayan, Gonçalo Simões, Yao Zhao, Joshua Maynez, Dipanjan Das, Michael Collins, Mirella Lapata

Figure 1 for A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation
Figure 2 for A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation
Figure 3 for A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation
Figure 4 for A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation
Viaarxiv icon

Measuring Attribution in Natural Language Generation Models

Dec 23, 2021
Hannah Rashkin, Vitaly Nikolaev, Matthew Lamm, Michael Collins, Dipanjan Das, Slav Petrov, Gaurav Singh Tomar, Iulia Turc, David Reitter

Figure 1 for Measuring Attribution in Natural Language Generation Models
Figure 2 for Measuring Attribution in Natural Language Generation Models
Figure 3 for Measuring Attribution in Natural Language Generation Models
Figure 4 for Measuring Attribution in Natural Language Generation Models
Viaarxiv icon

Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss

Aug 16, 2021
Thomas Effland, Michael Collins

Figure 1 for Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss
Figure 2 for Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss
Figure 3 for Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss
Figure 4 for Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss
Viaarxiv icon

On planetary systems as ordered sequences

May 20, 2021
Emily Sandford, David Kipping, Michael Collins

Figure 1 for On planetary systems as ordered sequences
Figure 2 for On planetary systems as ordered sequences
Figure 3 for On planetary systems as ordered sequences
Figure 4 for On planetary systems as ordered sequences
Viaarxiv icon

Decontextualization: Making Sentences Stand-Alone

Feb 09, 2021
Eunsol Choi, Jennimaria Palomaki, Matthew Lamm, Tom Kwiatkowski, Dipanjan Das, Michael Collins

Figure 1 for Decontextualization: Making Sentences Stand-Alone
Figure 2 for Decontextualization: Making Sentences Stand-Alone
Figure 3 for Decontextualization: Making Sentences Stand-Alone
Figure 4 for Decontextualization: Making Sentences Stand-Alone
Viaarxiv icon

NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

Jan 01, 2021
Sewon Min, Jordan Boyd-Graber, Chris Alberti, Danqi Chen, Eunsol Choi, Michael Collins, Kelvin Guu, Hannaneh Hajishirzi, Kenton Lee, Jennimaria Palomaki, Colin Raffel, Adam Roberts, Tom Kwiatkowski, Patrick Lewis, Yuxiang Wu, Heinrich Küttler, Linqing Liu, Pasquale Minervini, Pontus Stenetorp, Sebastian Riedel, Sohee Yang, Minjoon Seo, Gautier Izacard, Fabio Petroni, Lucas Hosseini, Nicola De Cao, Edouard Grave, Ikuya Yamada, Sonse Shimaoka, Masatoshi Suzuki, Shumpei Miyawaki, Shun Sato, Ryo Takahashi, Jun Suzuki, Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz, Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao, Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Wen-tau Yih

Figure 1 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Figure 2 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Figure 3 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Figure 4 for NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned
Viaarxiv icon

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?
Viaarxiv icon

QED: A Framework and Dataset for Explanations in Question Answering

Sep 08, 2020
Matthew Lamm, Jennimaria Palomaki, Chris Alberti, Daniel Andor, Eunsol Choi, Livio Baldini Soares, Michael Collins

Figure 1 for QED: A Framework and Dataset for Explanations in Question Answering
Figure 2 for QED: A Framework and Dataset for Explanations in Question Answering
Figure 3 for QED: A Framework and Dataset for Explanations in Question Answering
Figure 4 for QED: A Framework and Dataset for Explanations in Question Answering
Viaarxiv icon

Sparse, Dense, and Attentional Representations for Text Retrieval

May 01, 2020
Yi Luan, Jacob Eisenstein, Kristina Toutanova, Michael Collins

Figure 1 for Sparse, Dense, and Attentional Representations for Text Retrieval
Figure 2 for Sparse, Dense, and Attentional Representations for Text Retrieval
Figure 3 for Sparse, Dense, and Attentional Representations for Text Retrieval
Figure 4 for Sparse, Dense, and Attentional Representations for Text Retrieval
Viaarxiv icon