I am a third-year PhD student of Language Technology Institute in the School of Computer Science at Carnegie Mellon University. I am fortunate to be co-advised by Prof. Graham Neubig and Prof. Taylor Berg-Kirkpatrick, Before that, I received bachelor degree in Electronic Engineering from Shanghai Jiao Tong University

My principal interests lie in the area of machine learning, particularly in statistical machine learning and unsupervised learning. I am also interested in the application of machine learning methods in natural language processing.



  • Revisiting Self-Training for Neural Sequence Generation
    Junxian He*, Jiatao Gu* (equal contribution), Jiajun Shen, Marc'Aurelio Ranzato
    ICLR 2020. [arxiv] [code]
  • A Probabilistic Formulation of Unsupervised Text Style Transfer
    Junxian He*, Xinyi Wang* (equal contribution), Graham Neubig, Taylor Berg-Kirkpatrick
    ICLR 2020 (spotlight). [arxiv] [code]
  • A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text
    Bohan Li*, Junxian He* (equal contribution), Graham Neubig, Taylor Berg-Kirkpatrick, Yiming Yang
    EMNLP 2019 (short paper). [arxiv] [code]
  • Cross-Lingual Syntactic Transfer through Unsupervised Adaptation of Invertible Projections
    Junxian He, Zhisong Zhang, Taylor Berg-Kirkpatrick, Graham Neubig
    ACL 2019. [arxiv] [code]
  • Texar: A modularized, versatile, and extensible toolkit for text generation
    Zhiting Hu, Haoran Shi, Bowen Tan, Wentao Wang, Zichao Yang, Tiancheng Zhao, Junxian He, Lianhui Qin, Di Wang, Xuezhe Ma, Zhengzhong Liu, Xiaodan Liang, Wangrong Zhu, Devendra Singh Sachan, Eric P. Xing
    ACL 2019 (demo paper). Best demo paper nomination. [arxiv] [GitHub]
  • Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
    Junxian He, Daniel Spokoyny, Graham Neubig, Taylor Berg-Kirkpatrick
    ICLR 2019. [arxiv] [code]
  • Unsupervised Learning of Syntactic Structure with Invertible Neural Projections
    Junxian He, Graham Neubig, Taylor Berg-Kirkpatrick
    EMNLP 2018, oral. [arxiv] [code]
  • StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing
    Pengcheng Yin, Chunting Zhou, Junxian He, Graham Neubig
    ACL 2018, oral. [arxiv]
  • Efficient Correlated Topic Modeling with Topic Embedding
    Junxian He*, Zhiting Hu* (equal contribution), Taylor Berg-Kirkpatrick, Ying Huang, Eric Xing
    KDD 2017, oral. [arxiv]
  • Text Network Exploration via Heterogeneous Web of Topics
    Junxian He, Ying Huang, Changfeng Liu, Jiaming Shen, Yuting Jia, Xinbing Wang
    ICDM 2016 WorkShop. [arxiv] [demo]