Yanshuai Cao 曹颜帅

Ph.D. | Senior Research Team Lead @Borealis AI (RBC)

Currently I lead an R&D team to conduct research and build products for financial services. I have worked on a range of topics across deep learning, generative models, adversarial machine learning, NLP and computer vision. I obtained my Ph.D. under David J. Fleet and Aaron Hertzmann at the University of Toronto.

news

Aug 1, 2021 We are presenting the following 4 papers at ACL 2021: These four papers highlight some of our works from last year on precise sentence level semantics. A common theme here is on solving hard NLU problems when high quality labelled data is scarce. For more information, check out the page on our Text-to-SQL system.
Jun 14, 2021 We launched a public page about our Text-to-SQL system and related works, including papers, blogs and live demo. Also check out this blog I wrote on “Why is Cross-Domain Text-to-SQL Hard?”.
Jan 1, 2021 New arxiv papers Optimizing Deeper Transformers on Small Datasets and Code Generation from Natural Language with Less Prior Knowledge and More Monolingual Data online !
Dec 15, 2020 This new personal site is live!

Selected Publications:

* denotes equal contribution

  1. ACL
    Code Generation from Natural Language with Less Prior Knowledge and More Monolingual Data
    Sajad Norouzi, Keyi Tang, and Yanshuai Cao
    In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics 2021
  2. ACL
    Optimizing Deeper Transformers on Small Datasets
    Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J.D. Prince, and Yanshuai Cao
    In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics 2021
  3. AISTATS
    Better Long-Range Dependency By Bootstrapping A Mutual Information Regularizer
    Yanshuai Cao*, and Peng Xu*
    In Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics 2020
  4. ICML
    Evaluating Lossy Compression Rates of Deep Generative Models
    Sicong Huang*, Alireza Makhzani*, Yanshuai Cao, and Roger Grosse
    In Proceedings of the 37th International Conference on Machine Learning 2020
  5. ICML
    On Variational Learning of Controllable Representations for Text without Supervision
    Peng Xu, Jackie Chi Kit Cheung, and Yanshuai Cao
    In Proceedings of the 37th International Conference on Machine Learning 2020
  6. ICLR
    Improving GAN Training via Binarized Representation Entropy (BRE) Regularization
    Yanshuai Cao, Gavin Weiguang Ding, Kry Yik-Chau Lui, and Ruitong Huang
    International Conference on Learning Representations, ICLR 2018
  7. ACL
    Adversarial Contrastive Estimation
    Avishek Joey Bose*, Huan Ling*, and Yanshuai Cao*
    In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2018