Alert button
Picture for Kelvin Guu

Kelvin Guu

Alert button

Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations

Apr 15, 2021
Jonathan Herzig, Peter Shaw, Ming-Wei Chang, Kelvin Guu, Panupong Pasupat, Yuan Zhang

Figure 1 for Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations
Figure 2 for Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations
Figure 3 for Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations
Figure 4 for Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations
Viaarxiv icon

Neural Data Augmentation via Example Extrapolation

Feb 02, 2021
Kenton Lee, Kelvin Guu, Luheng He, Tim Dozat, Hyung Won Chung

Figure 1 for Neural Data Augmentation via Example Extrapolation
Figure 2 for Neural Data Augmentation via Example Extrapolation
Figure 3 for Neural Data Augmentation via Example Extrapolation
Figure 4 for Neural Data Augmentation via Example Extrapolation
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

Learning Abstract Models for Strategic Exploration and Fast Reward Transfer

Jul 12, 2020
Evan Zheran Liu, Ramtin Keramati, Sudarshan Seshadri, Kelvin Guu, Panupong Pasupat, Emma Brunskill, Percy Liang

Figure 1 for Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
Figure 2 for Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
Figure 3 for Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
Figure 4 for Learning Abstract Models for Strategic Exploration and Fast Reward Transfer
Viaarxiv icon

Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models

May 20, 2020
Dan Iter, Kelvin Guu, Larry Lansing, Dan Jurafsky

Figure 1 for Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models
Figure 2 for Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models
Figure 3 for Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models
Figure 4 for Pretraining with Contrastive Sentence Objectives Improves Discourse Performance of Language Models
Viaarxiv icon

REALM: Retrieval-Augmented Language Model Pre-Training

Feb 10, 2020
Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, Ming-Wei Chang

Figure 1 for REALM: Retrieval-Augmented Language Model Pre-Training
Figure 2 for REALM: Retrieval-Augmented Language Model Pre-Training
Figure 3 for REALM: Retrieval-Augmented Language Model Pre-Training
Figure 4 for REALM: Retrieval-Augmented Language Model Pre-Training
Viaarxiv icon

KERMIT: Generative Insertion-Based Modeling for Sequences

Jun 04, 2019
William Chan, Nikita Kitaev, Kelvin Guu, Mitchell Stern, Jakob Uszkoreit

Figure 1 for KERMIT: Generative Insertion-Based Modeling for Sequences
Figure 2 for KERMIT: Generative Insertion-Based Modeling for Sequences
Figure 3 for KERMIT: Generative Insertion-Based Modeling for Sequences
Figure 4 for KERMIT: Generative Insertion-Based Modeling for Sequences
Viaarxiv icon

A Retrieve-and-Edit Framework for Predicting Structured Outputs

Dec 04, 2018
Tatsunori B. Hashimoto, Kelvin Guu, Yonatan Oren, Percy Liang

Figure 1 for A Retrieve-and-Edit Framework for Predicting Structured Outputs
Figure 2 for A Retrieve-and-Edit Framework for Predicting Structured Outputs
Figure 3 for A Retrieve-and-Edit Framework for Predicting Structured Outputs
Figure 4 for A Retrieve-and-Edit Framework for Predicting Structured Outputs
Viaarxiv icon

Mapping Natural Language Commands to Web Elements

Oct 01, 2018
Panupong Pasupat, Tian-Shun Jiang, Evan Zheran Liu, Kelvin Guu, Percy Liang

Figure 1 for Mapping Natural Language Commands to Web Elements
Figure 2 for Mapping Natural Language Commands to Web Elements
Figure 3 for Mapping Natural Language Commands to Web Elements
Figure 4 for Mapping Natural Language Commands to Web Elements
Viaarxiv icon

Transforming Question Answering Datasets Into Natural Language Inference Datasets

Sep 11, 2018
Dorottya Demszky, Kelvin Guu, Percy Liang

Figure 1 for Transforming Question Answering Datasets Into Natural Language Inference Datasets
Figure 2 for Transforming Question Answering Datasets Into Natural Language Inference Datasets
Figure 3 for Transforming Question Answering Datasets Into Natural Language Inference Datasets
Figure 4 for Transforming Question Answering Datasets Into Natural Language Inference Datasets
Viaarxiv icon