Shining Lab

Ning Shi (石宁)

shininglab.png

Amii, UAlberta CS

Edmonton, Alberta, CA

I am a Ph.D. student at the University of Alberta, associated with the Alberta Machine Intelligence Institute (Amii). Previously, I was a senior algorithm engineer at Alibaba Group, Alibaba Artificial Intelligence Governance Laboratory (AAIG).

My research interests lie in the broad area of computational linguistics, natural language processing, reinforcement learning, and their applications. In particular, from the perspective of human cognition, I am interested in the extent to which neural networks can do the same (or even better?) as humans to understand the world systematically.

I hold a research group called Shining Lab where ideas shine! For any research opportunity or collaboration, please feel free to get in touch.

news

Jul 4, 2023 Please redirect to my latest personal homepage.

selected publications

2023

  1. arXiv
    Interactive natural language processing
    Zekun Wang, Ge Zhang, Kexin Yang, Ning Shi, Wangchunshu Zhou, Shaochun Hao, Guangzheng Xiong, Yizhi Li, Mong Yuan Sim, Xiuying Chen, and  others
    arXiv preprint arXiv:2305.13246, 2023

2022

  1. BlackboxNLP
    Revisit Systematic Generalization via Meaningful Learning
    Ning Shi, Boxin Wang, Wei Wang, Xiangyu Liu, and Zhouhan Lin
    In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, Dec 2022
  2. EMNLP Findings
    Text Editing as Imitation Game
    Ning Shi, Bin Tang, Bo Yuan, Longtao Huang, Yewen Pu, Jie Fu, and Zhouhan Lin
    In Findings of the Association for Computational Linguistics: EMNLP 2022, Dec 2022

2021

  1. INTERSPEECH
    Incorporating External POS Tagger for Punctuation Restoration
    Ning Shi, Wei Wang, Boxin Wang, Jinfeng Li, Xiangyu Liu, and Zhouhan Lin
    In Proc. Interspeech 2021, Dec 2021

2020

  1. EMNLP Findings
    Recurrent Inference in Text Editing
    Ning Shi, Ziheng Zeng, Haotian Zhang, and Yichen Gong
    In Findings of the Association for Computational Linguistics: EMNLP 2020, Nov 2020