Lili Mou, PhD

Note: I am moving my homepage from to
because the pku server is unavailable from time to time.
However, the html style remains unchanged, so that it is
familiar to you all my friends.

Email: doublepower [dot] mou [at] gmail [dot] com

Lili Mou is currently a postdoctoral fellow at the University of Waterloo. Lili received his BS and PhD degrees in 2012 and 2017, respectively, from School of EECS, Peking University. After that, he worked as a postdoctoral fellow at the University of Waterloo and a research scientist at Adeptmind (a startup in Toronto, Canada). His research interests include deep learning applied to natural language processing as well as programming language processing. He has publications at top conferences and journals like AAAI, ACL, CIKM, COLING, EMNLP, ICASSP, ICML, IJCAI, INTERSPEECH, NAACL-HLT, and TACL (in alphabetic order). [CV]


In our seminars, we discuss machine learning theories, algorithms,
and applications (with special interest in NLP). We start from the foundations,
and move to the frontiers.

Please visit here for contents.


Copyright announcement: Copyrights of published papers might be held by publishers. All rights are reserved for other materials, including drafts, slides, and source code. Whenever not conflicting with copyright laws, I permit free use for non-commerical purposes. Please cite my papers if you use them for research. In particular, if a paper is accompanied with source code, the URL is available in the paper. Please notice, however, there's no guarantee that my code is executable in your environment.

Useful links: Complete list, Google Scholar, DBLP


  • Lili Mou, Zhi Jin. Tree-Based Convolutional Neural Networks: Principles and Applications, Springer, 2018. [url]


  • Hareesh Bahuleyan, Lili Mou, Hao Zhou, Olga Vechtomova. Probabilistic natural language generation with Wasserstein autoencoders. To appear in NAACL-HLT, 2019.

  • Zeyu Sun, Qihao Zhu, Lili Mou, Yingfei Xiong, Ge Li, Lu Zhang. A grammar-based structural CNN decoder for code generation. To appear in AAAI, 2019. [pdf]

  • Ning Miao, Hao Zhou, Lili Mou, Rui Yan, Lei Li. CGMH: Constrained sentence generation by Metropolis-Hastings sampling. To appear in AAAI, 2019.

  • Bolin Wei,1 Shuai Lu,1 Lili Mou, Hao Zhou, Pascal Poupart, Ge Li, Zhi Jin. Why do neural dialog systems generate short and meaningless replies? A comparison between dialog and translation. In Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 7290--7294, 2019. [pdf]

Selected Refereed Papers

[Selection is NOT based on the venue or length of a paper.]
  • Hareesh Bahuleyan,1 Lili Mou,1 Olga Vechtomova, Pascal Poupart. Variational attention for sequence-to-sequence models. In Proceedings of the International Conference on Computational Linguistics (COLING), pages 1672-1682, 2018. Also presented at TADGM Workshop @ICML, 2018. [pdf, slides]

  • Lili Mou, Zhengdong Lu, Hang Li, Zhi Jin. Coupling distributed and symbolic execution for natural language queries. In Proceedings of the 34th International Conference on Machine Learning (ICML), pages 2518--2526, 2017. Also presented in ICLR Workshop, 2017. [pdf, slides (courtesy of ZL), slides]

  • Lili Mou, Zhao Meng, Rui Yan, Ge Li, Yan Xu, Lu Zhang, Zhi Jin. How transferable are neural networks in NLP applications? In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 478--489, 2016. [pdf]

  • Yunchuan Chen, Lili Mou, Yan Xu, Ge Li, Zhi Jin. Compressing neural language models by sparse word representations. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL), pages 226--235, 2016. [pdf]

  • Lili Mou, Ge Li, Lu Zhang, Tao Wang, Zhi Jin. Convolutional neural networks over tree structures for programming language processing. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI), pages 1287--1293, 2016. [pdf]

  • Lili Mou,1 Hao Peng,1 Ge Li, Yan Xu, Lu Zhang, Zhi Jin. Discriminative neural sentence modeling by tree-based convolution. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2315--2325, 2015. [pdf, slides]

  • Yan Xu, Lili Mou, Ge Li, Yunchuan Chen, Hao Peng and Zhi Jin. Classifying relations via long short term memory networks along shortest dependency paths. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1785--1794, 2015. [pdf, slides (courtesy of YX)]

1=equal contribution.

Academic Service

Primary reviewer: NAACL'16 (best reviewers), COLING'16, ACL'17, AAAI'18, NAACL'18, ACL'18, COLING'18 (PC and Mentor), Computer Speech & Language, TKDE
Subreviewer: FSE'16, BigData'17, AAAI'17, IJCAI'18Cognitive Computing, JCST


Lili Mou, Hao Zhou, Lei Li. Discreteness in Neural Natural Language Processing. Accepted as an EMNLP-IJCNLP Tutorial, 2019.

Teaching Experience

Co-Supervised Students

Hao Peng (undergraduate)
with publication at
Rui Men (undergraduate)
with publication at
Zhao Meng (undergraduate)
with publications at
EMNLP-16, CIKM-17 & AAAI-18 (student poster).
Bolin Wei (undergraduate
-> master student) with
publication at ICASSP-19.
Yiping Song (PhD student)
with publication at
Hareesh Bahuleyan (master student) with publication
at COLING-18 & NAACL-19.
Nabiha Asghar (PhD student)
with arXiv preprint

Teaching Assistant

2012.9--2013.1   TA of Introduction to Computing (undergraduate course)
Lecture (Dec 2012): Minimax and Alpha-Beta Pruning [slides in Chinese]
2013.2--2013.6 TA of Java Programming (graduate course)
2013.9--2014.1 TA of Introduction to Programming Languages (undergraduate course)
TA of Introduction to Computing (MOOC)
2014.9--2015.1 TA of Introduction to Computing (MOOC)
2015.3--2015.6 TA of Deep Learning Techniques and Applications (graduate course)
2016.2--2016.6 TA of Deep Learning Techniques and Applications (graduate course)
Lecture (5 May 2016): Neural Networks for Natural Language Processing [slides]
Guest Lecture of "Deep Learning Techniques and Applications" course (11 May 2017):
Neural Networks in NLP: The Curse of Indifferentiability [slides: I, II, III]
Mini-Project Tutorial for Undergrad. Res. Opportunities Conf. @ U Waterloo (22 and 23 Sep 2017):
Adversarial Training and Security in Machine Learning [slides, code]


Lili Mou's major hobbies include practicing calligraphy, watching yueju,
visiting traditional Chinese architectures, taking MOOCs, and many others.