About Me

Hello, I am a fourth-year Ph.D. student at the Department of Computer Science, University of California, Santa Barbara, fortunately advised by Prof. Xifeng Yan. Prior to that, I obtained my B.Eng. degree in Computer Science and Technology with honors from Harbin Institute of Technology (HIT), Harbin, China.

I have broad research interests :). I am currently working on natural language processing. Before that, I ever worked on time series forecasting and computer vision.

Publications

• Task-adaptive Pre-training and Self-training are Complementary for Natural Language Understanding
  Shiyang Li, Semih Yavuz, Wenhu Chen and Xifeng Yan [paper]
  Findings of the Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP), Long paper, 2021

• CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
  Shiyang Li*, Semih Yavuz*, Kazuma Hashimoto, Jia Li, Tong Niu, Nazneen Rajani, Xifeng Yan, Yingbo Zhou and Caiming Xiong (*Equal Contribution) [paper]
  International Conference on Learning Representations (ICLR), 2021

• TabFact: A Large-scale Dataset for Table-based Fact Verification
  Wenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang, Hong Wang, Shiyang Li, Xiyou Zhou and William Yang Wang
  [paper] [website] [code and data]
  International Conference on Learning Representations (ICLR), 2020

• Teaching Pretrained Models with Commonsense Reasoning: A Preliminary KB-Based Approach
  Shiyang Li, Jianshu Chen and Dian Yu [paper]
  Knowledge Representation & Reasoning Meets Machine Learning Workshop at NeurIPS 2019

• Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
  Shiyang Li, Xiaoyong Jin, Yao Xuan, Xiyou Zhou, Wenhu Chen, Yu-Xiang Wang and Xifeng Yan [paper]
  Advances in Neural Information Processing Systems (NeurIPS), 2019

• HierCon: Hierarchical Organization of Technical Documents based on Concepts
  Keqian Li, Shiyang Li, Semih Yavuz, Hanwen Zha, Yu Su, and Xifeng Yan
  IEEE International Conference on Data Mining (IEEE ICDM), 2019 (Regular, acceptance rate: 9.08%) [paper]
  Selected as one of the best papers of ICDM 2019 and invited for potential publication at the KAIS Journal

• Multi-step Deep Autoregressive Forecasting with Latent States
  Xiaoyong Jin, Shiyang Li, Yunkai Zhang and Xifeng Yan [paper]
  ICML 2019 Workshop on Time Series

• Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Distributed Nonconvex Stochastic Optimization
  Tianyi Liu, Shiyang Li, Jianping Shi, Enlu Zhou and Tuo Zhao [paper]
  Advances in Neural Information Processing Systems (NeurIPS), 2018

Experience

• Microsoft
  Jun. 2021 - Sep. 2021, Seattle, WA, U.S.A.
  Research Intern
  Mentor: Dr. Yelong Shen

• Salesforce Research
  Jun. 2020 - Dec. 2020, Palo Alto, CA, U.S.A.
  Research Intern
  Mentor: Dr. Semih Yavuz

• Tencent AI Lab
  Jun. 2019 - Sep. 2019, Bellevue, WA, U.S.A.
  Research Intern, NLP Group
  Mentor: Dr. Jianshu Chen

• SenseTime
  Nov. 2017 - Aug. 2018, Beijing, China
  Research Intern, Segmentation Group
  Mentor: Dr. Guangliang Cheng and Dr. Jianping Shi

Academic Service

• Reviewer: ICML 2020, NeurIPS 2020, ICLR 2021, 2022

Honors and Awards

• Best paper candidate, IEEE ICDM  2019
• NeurIPS Travel Award   2018, 2019
• Outstanding Scholar Fellowship, Department of CS at UCSB   2018
• Academic Excellence Fellowship, Department of CS at UCSB   2018