Xiang Zhou

Ph.D. Student

University of North Carolina at Chapel Hill

About me

I’m currently a 4th-year Ph.D. student in the Department of Computer Science, UNC-Chapel Hill, working with Prof. Mohit Bansal.

I received my bachelor’s degree at Shanghai Jiao Tong University (SJTU) in 2018, where I worked with Prof. Kai Yu. I was a member of the IEEE honored class. I also spent one summer visiting the University of Notre Dame, working with Prof. David Chiang.

Previously, I worked with Jean Maillard at Facebook AI Research as a research intern, and worked with Heba Elfardy and Tom Butler as an applied scientist intern at Amazon.

My research interest lies in building NLP models that understands and analyzes language just like human. I still believe the right path is related to (implicitly) acquiring syntax.

Interests

Language
Syntax
Robustness and Generalization

Education

Ph.D. in Computer Science, 2018-Present

University of North Carolina at Chapel Hill
B.S.E. in Computer Science, 2014-2018

Shanghai Jiao Tong University

Publications

Xiang Zhou∗, Yixin Nie∗, Mohit Bansal. Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning. Preprint in arXiv, 2021.

Details PDF

Xiang Zhou, Heba Elfardy, Christos Christodoulopoulos, Thomas Butler, Mohit Bansal. Hidden Biases in Unreliable News Detection Datasets. (Best Long Paper Award Honorable Mention) In EACL, 2021.

Details PDF Code

Xiang Zhou, Yixin Nie, Hao Tan, Mohit Bansal. The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions. In EMNLP, 2020.

Details PDF Code

Yixin Nie, Xiang Zhou, Mohit Bansal. What Can We Learn from Collective Human Opinions on Natural Language Inference Data?. In EMNLP, 2020.

Details PDF Code

Xiang Zhou, Mohit Bansal. Towards Robustifying NLI Models Against Lexical Dataset Biases. In ACL, 2020.

Details PDF Code

Cheng Chang, Runzhe Yang, Lu Chen, Xiang Zhou, Kai Yu. Affordable On-line Dialogue Policy Learning. In EMNLP, 2017.

Details PDF Appendix

Lu Chen, Xiang Zhou, Cheng Chang, Runzhe Yang, Kai Yu. Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning. In EMNLP, 2017.

Details PDF Appendix

Lu Chen, Runzhe Yang, Cheng Chang, Zihao Ye, Xiang Zhou, Kai Yu. On-line Dialogue Policy Learning with Companion Teaching. In EACL, 2017.

Details PDF

Contact

xzh at cs dot unc dot edu