I am an assistant professor of Computer Science at Princeton University. Previously, I was a visiting scientist at Facebook AI Research (FAIR) in Seattle. I received my PhD from the Computer Science Department at Stanford University, where I was advised by Christopher Manning and worked in the Stanford NLP Group.
Before that, I was an undergraduate student from the Special Pilot CS Class supervised by Andrew Yao at Tsinghua University.
My main research interests lie within deep learning for natural language processing, and I am particularly interested in the intersection between text understanding and knowledge representation/reasoning.
Prospective students: I am actively looking for strong students to join my group! If you are interested in working with me, please apply through the Princeton CS PhD program and mention me in your application (and I can't respond to all the individual emails).
If you are already admitted to Princeton, feel free to reach out to me or come talk to me during my office hour.
Papers (*: equal contribution)
- Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering
Sewon Min, Danqi Chen, Luke Zettlemoyer, Hannaneh Hajishirzi.
- SpanBERT: Improving Pre-training by Representing and Predicting Spans
[bib] [arXiv] [code & models]
Mandar Joshi*, Danqi Chen*, Yinhan Liu, Daniel S. Weld, Luke Zettlemoyer, Omer Levy.
In TACL 2019 (to appear).
- MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension
[bib] [arXiv] [code & dataset]
Adam Fisch, Alon Talmor, Robin Jia, Minjoon Seo, Eunsol Choi, Danqi Chen
In MRQA 2019.
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
[bib] [arXiv] [code & models]
Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov.
- A Discrete Hard EM Approach for Weakly Supervised Question Answering
[bib] [paper] [arXiv] [code]
Sewon Min, Danqi Chen, Hannaneh Hajishirzi, Luke Zettlemoyer.
In EMNLP 2019.
- CoQA: A Conversational Question Answering Challenge
[bib] [paper] [arXiv] [code] [website]
Siva Reddy*, Danqi Chen*, Christopher D. Manning.
In TACL 2019.
Check out the dataset and leaderboard at https://stanfordnlp.github.io/coqa/.
- Reading Wikipedia to Answer Open-Domain Questions
[bib] [paper][arXiv] [code] [poster]
Danqi Chen, Adam Fisch, Jason Weston, Antoine Bordes.
In ACL 2017.
Check out our DrQA project on Github.
- Position-aware Attention and Supervised Data Improve Slot Filling
[bib] [paper] [code]
Yuhao Zhang, Victor Zhong, Danqi Chen, Gabor Angeli, and Christopher D. Mannning.
In EMNLP 2017 (Outstanding Paper Award).
- Stanford at TAC KBP 2016: Sealing Pipeline Leaks and Understanding Chinese
Yuhao Zhang*, Arun Chaganty*, Ashwin Paranjape*, Danqi Chen*, Jason Bolton*, Peng Qi, Christopher D. Manning.
In TAC 2016.
- A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
[bib] [acl paper] [arXiv] [slides] [code]
Danqi Chen, Jason Bolton, Christopher D. Manning.
In ACL 2016 (Outstanding Paper Award).
- Representing Text for Joint Embedding of Text and Knowledge Bases
[bib] [paper][FB15k-237 dataset]
Kristina Toutanova, Danqi Chen, Patrick Pantel, Hoifung Poon, Pallavi Choudhury, Michael Gamon.
In EMNLP 2015.
- Bootstrapped Self Training for Knowledge Base Population
Gabor Angeli, Victor Zhong, Danqi Chen, Arun Chaganty, Jason Bolton,
Melvin Johnson Premkumar, Panupong Pasupat, Sonal Gupta, Christopher D. Manning.
In TAC 2015.
- Observed Versus Latent Features for Knowledge Base and Text Inference
Kristina Toutanova, Danqi Chen.
In Workshop on Continuous Vector Space Models and Their Compositionality (CVSC) 2015.
- A Fast and Accurate Dependency Parser using Neural Networks
[bib] [paper] [slides] [website & code]
Danqi Chen, Christopher D. Manning.
In EMNLP 2014.
Our dependency parser is included in the Stanford CoreNLP software and the Stanford Parser (since v3.5.0).
- Reasoning With Neural Tensor Networks for Knowledge Base Completion
[bib] [paper] [poster] [data]
Richard Socher*, Danqi Chen*, Christopher D. Manning, Andrew Ng.
In NIPS 2013.
- Learning New Facts From Knowledge Bases With Neural Tensor Networks and Semantic Word Vectors
Danqi Chen, Richard Socher, Christopher D. Manning, Andrew Ng.
In ICLR 2013 (workshop track).
- Beyond Ten Blue Links: Enabling User Click Modeling in Federated Web Search
Danqi Chen, Weizhu Chen, Haixun Wang, Zheng Chen, Qiang Yang.
In WSDM 2012 (plenary presentation).
- Characterizing Inverse Time Dependency in Multi-class Learning
Danqi Chen, Weizhu Chen, Qiang Yang.
In ICDM 2011.
- 2012 - 2018: Ph.D. from Stanford University
- 2008 - 2012: B.Eng from Yao Class, Tsinghua University
- 2010 Fall: Exchange student at Hong Kong University of Science and Technology (HKUST)
- 2019/2-2019/8: Visiting Scientist at Facebook AI Research, Seattle
- 2016.10 - 2016.12: Research intern at Facebook AI Research, NYC
Working with Antoine Bordes, Jason Weston
- 2014.7 - 2014.9: Research intern at Microsoft Research Redmond (NLP group)
Working with Kristina Toutanova, Hoifung Poon, Patrick Pantel, Michael Gamon
- 2011.2 - 2012.5: Research intern at Microsoft Research Asia (ML & WSM group)
Working with Weizhu Chen, Haixun Wang
Honors and awards
- Facebook Fellowship, 2017-2019
- Outstanding Paper Awards in ACL 2016 and EMNLP 2017
- Microsoft Research Women’s Fellowship, 2013-2014
- Outstanding Graduate Award, Tsinghua University, 2012
- Outstanding Undergraduate Dissertation Award, Tsinghua University, 2012
- Silver Medal of Yao Award, 2011
- Top Scholarship for Freshman and Comprehensive Merit Scholarship × 3, Tsinghua University, 2008-2012
- ACM ICPC contests: Silver Medal in World Finals 2010 (6th place overall), champions × 3 and Gold Medals × 7 in Asian regional contests, 2008-2010
- Gold Medal in International Olympiad in Informatics, 2008
- Organizing committee:
- Area Chair:
- ACL 2020 (Sentence-level Semantics)
- AKBC 2020 (Question Answering and Reasoning)
- EMNLP 2019 (Question Answering)
- Program committee/reviewing:
- Conference: ACL, EMNLP, NAACL, NeurIPS, ICML, ICLR, AAAI, EACL, CoNLL, COLING, IJCNLP, *SEM
- Journal: TACL, TKDE
Last updated: 2019/09.
- My name is pronounced as "dan-/'chE/" (read this). My friends like to call me "CDQ" though.
- I come from Changsha, China. In the past, I have also lived in Beijing, Hong Kong, Palo Alto, New York, Boston and Seattle.
- Here are two papers that I wrote in high school (in Chinese):  and  and they are known as "plug-like dynamic programming" and "CDQ's divide-and-conquer" today.
- Whenever I am not thinking about research, I enjoy most of outdoor activities and also spend a lot of time on reading, movies & exploring restaurants.
- Some of my portraits: 1, 2, 3 (credit: Lu Wang).
- I am on Twitter.