Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering

May 05, 2020
Hao Cheng, Ming-Wei Chang, Kenton Lee, Kristina Toutanova

* ACL2020 

  Access Model/Code and Paper
REALM: Retrieval-Augmented Language Model Pre-Training

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


  Access Model/Code and Paper
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models

Sep 25, 2019
Iulia Turc, Ming-Wei Chang, Kenton Lee, Kristina Toutanova

* Added comparison to concurrent work 

  Access Model/Code and Paper
Well-Read Students Learn Better: The Impact of Student Initialization on Knowledge Distillation

Aug 23, 2019
Iulia Turc, Ming-Wei Chang, Kenton Lee, Kristina Toutanova


  Access Model/Code and Paper
Zero-Shot Entity Linking by Reading Entity Descriptions

Jun 18, 2019
Lajanugen Logeswaran, Ming-Wei Chang, Kenton Lee, Kristina Toutanova, Jacob Devlin, Honglak Lee

* ACL 2019 

  Access Model/Code and Paper
Latent Retrieval for Weakly Supervised Open Domain Question Answering

Jun 06, 2019
Kenton Lee, Ming-Wei Chang, Kristina Toutanova

* Accepted to ACL 2019 

  Access Model/Code and Paper
Handling Divergent Reference Texts when Evaluating Table-to-Text Generation

Jun 03, 2019
Bhuwan Dhingra, Manaal Faruqui, Ankur Parikh, Ming-Wei Chang, Dipanjan Das, William W. Cohen

* To appear at ACL 2019 

  Access Model/Code and Paper
BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

May 24, 2019
Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, Kristina Toutanova

* In NAACL 2019 

  Access Model/Code and Paper
Language Model Pre-training for Hierarchical Document Representations

Jan 26, 2019
Ming-Wei Chang, Kristina Toutanova, Kenton Lee, Jacob Devlin


  Access Model/Code and Paper
Improving Span-based Question Answering Systems with Coarsely Labeled Data

Nov 05, 2018
Hao Cheng, Ming-Wei Chang, Kenton Lee, Ankur Parikh, Michael Collins, Kristina Toutanova


  Access Model/Code and Paper
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Oct 11, 2018
Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova

* 13 pages 

  Access Model/Code and Paper
Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations

Sep 05, 2018
Dipendra Misra, Ming-Wei Chang, Xiaodong He, Wen-tau Yih

* Accepted at EMNLP 2018 

  Access Model/Code and Paper
Link Prediction using Embedded Knowledge Graphs

Apr 22, 2018
Yelong Shen, Po-Sen Huang, Ming-Wei Chang, Jianfeng Gao


  Access Model/Code and Paper
A Knowledge-Grounded Neural Conversation Model

Feb 07, 2017
Marjan Ghazvininejad, Chris Brockett, Ming-Wei Chang, Bill Dolan, Jianfeng Gao, Wen-tau Yih, Michel Galley

* 10 pages 

  Access Model/Code and Paper
Annotating Derivations: A New Evaluation Strategy and Dataset for Algebra Word Problems

Jan 10, 2017
Shyam Upadhyay, Ming-Wei Chang

* EACL 2017 long paper 

  Access Model/Code and Paper
Answering Complicated Question Intents Expressed in Decomposed Question Sequences

Nov 04, 2016
Mohit Iyyer, Wen-tau Yih, Ming-Wei Chang


  Access Model/Code and Paper
Toward Socially-Infused Information Extraction: Embedding Authors, Mentions, and Entities

Sep 26, 2016
Yi Yang, Ming-Wei Chang, Jacob Eisenstein

* Accepted to EMNLP 2016 

  Access Model/Code and Paper
S-MART: Novel Tree-based Structured Learning Algorithms Applied to Tweet Entity Linking

Sep 26, 2016
Yi Yang, Ming-Wei Chang

* Appeared in ACL 2015 proceedings. This is an updated version. More details available in the pdf file 

  Access Model/Code and Paper
IllinoisSL: A JAVA Library for Structured Prediction

Sep 23, 2015
Kai-Wei Chang, Shyam Upadhyay, Ming-Wei Chang, Vivek Srikumar, Dan Roth

* http://cogcomp.cs.illinois.edu/software/illinois-sl 

  Access Model/Code and Paper
Inferring Missing Entity Type Instances for Knowledge Base Completion: New Dataset and Methods

Apr 24, 2015
Arvind Neelakantan, Ming-Wei Chang

* North American Chapter of the Association for Computational Linguistics- Human Language Technologies, 2015 

  Access Model/Code and Paper