Research Interests

Deep Learning, Natural Language Processing, Computer Vision

Publications

• Self-training with Noisy Student improves ImageNet classification
  Qizhe Xie, Minh-Thang Luong, Eduard Hovy and Quoc V. Le.
  CVPR 2020 [SOTA ImageNet models] [code] [AI Index Report] [video]
  Tweets: [Quoc Le] [Jeff Dean] [Ilya Sutskever]

• Unsupervised Data Augmentation for Consistency Training
  Qizhe Xie, Zihang Dai, Eduard Hovy, Minh-Thang Luong and Quoc V. Le.
  [code] [Google blogpost] [Top-3 paper for last year by arxiv-sanity (Mar 2020)]

• Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation
  Xiang Kong, Qizhe Xie, Zihang Dai and Eduard Hovy.
  AAAI 2019

• From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction
  Zihang Dai*, Qizhe Xie* and Eduard Hovy. (*: equal contribution)
  ACL 2018 [code] [poster]

• Large-scale Cloze Test Dataset Created by Teachers
  Qizhe Xie*, Guokun Lai*, Zihang Dai and Eduard Hovy. (*: equal contribution)
  EMNLP 2018 [leaderboard] [data] [code]

• Controllable Invariance through Adversarial Feature Learning
  Qizhe Xie, Zihang Dai, Yulun Du, Eduard Hovy and Graham Neubig.
  NIPS 2017 [slides] [code]

• RACE: Large-scale ReAding Comprehension Dataset From Examinations
  Guokun Lai*, Qizhe Xie*, Hanxiao Liu, Yiming Yang and Eduard Hovy. (*: equal contribution)
  EMNLP 2017 [leaderboard] [data] [code] [slides]

• An Interpretable Knowledge Transfer Model for Knowledge Base Completion
  Qizhe Xie, Xuezhe Ma, Zihang Dai and Eduard Hovy.
  ACL 2017 [slides]

• Recurrent Polynomial Network for Dialogue State Tracking
  Kai Sun, Qizhe Xie and Kai Yu.
  Dialogue & Discourse 2016

• Recurrent Polynomial Network for Dialogue State Tracking with Mismatched Semantic Parsers
  Qizhe Xie, Kai Sun, Su Zhu, Lu Chen and Kai Yu.
  SigDial 2015 (Oral)

Previous Experiences

Work

• Student Researcher @ Google Brain 2018 May - Present
  Host: Quoc V. Le and Thang Luong

• Research Intern @ Microsoft Research Asia 2015 July - 2016 Jan.
  Host: Tie-Yan Liu, Bin Gao and Di He

Education

• Master @ Language Technologies Institute, Carnegie Mellon University 2016 - 2018
  Advisor: Eduard Hovy

• Undergrad @ ACM Honored Class, Zhiyuan College, Shanghai Jiao Tong University 2012 - 2016
  Advisor: Kai Yu

• High school @ Changjun High School 2009 - 2012
  Olympiad in Informatics Group