Zining Zhu (朱子宁)

PhD Student, University of Toronto

zining@cs.toronto.edu

Research interests: Interpretability, NLP + Society.

My long-term goal is to build reliable and trustworthy NLP systems that can be stably deployed across different domains. I am interested in understanding the mechanisms and abilities of neural NLP systems encoding and using knowledge, with language as a medium. I am also interested in the impacts of NLP systems to societies.
I write articles at this blog, and upload videos discussing NLP papers to this YouTube channel.


Selected Publications

Show all Show selected
    2020
  • An information theoretic view on selecting linguistic probes
    Zining Zhu, Frank Rudzicz. EMNLP 2020
    paper blog bib
  • Examining the rhetorical capacities of neural language models
    Zining Zhu, Chuer Pan, Mohamed Abdalla, Frank Rudzicz. EMNLP 2020 BlackboxNLP Workshop
    paper blog bib
  • Semantic coordinates analysis reveals language changes in the AI field
    Zining Zhu, Yang Xu, Frank Rudzicz. arXiv preprint 2011.00543
    paper bib
  • 2019
  • Detecting Cognitive Impairments by Agreeing on Interpretations of Linguistic Features
    Zining Zhu, Jekaterina Novikova, Frank Rudzicz. NAACL 2019
    paper bib
  • Natural Languages Understanding by a Compositional Alignment of Word Embeddings
    Zining Zhu. Engineering Science Undergraduate Thesis (supervisor: Frank Rudzicz)
    paper blog bib
  • 2018
  • Semi-Supervised Classification by Reaching Consensus among Modalities
    Zining Zhu, Jekaterina Novikova, Frank Rudzicz. NeurIPS 2018 IRASL Workshop
    paper bib
  • Deconfounding Age Effects with Fair Representation Learning When Assessing Dementia
    Zining Zhu, Jekaterina Novikova, Frank Rudzicz. arXiv preprint 1807.07217
    paper press slides bib
  • Robuatness Against the Channel Effect in Pathological Voice Detection
    Yi-Te Hsu, Zining Zhu, Chi-Te Wang, Shih-Hau Fang, Frank Rudzicz, Yu Tsao. NeurIPS 2018 ML4H Workshop
    paper bib
  • 2017
  • Deep Neural Networks for Improved, Impromptu Trajectory Tracking of Quadrotors
    Qiyang Li, Jingxing Qian, Zining Zhu, Xuchan Bao, Mohamed K. Helwa, Angela P. Schoellig. ICRA 2017
    paper blog bib

Experience

Education

University of Toronto 2019 - 2024 (Expected)
Ph.D student in Computer Science
Supervisor: Frank Rudzicz
University of Toronto 2014 - 2019
Bachelor in Engineering Science, Robotics option.

Work / Research

Tencent Jarvis Lab, Machine Learning Engineering Intern, May 2019 - Aug 2019
Neural language models and pre-training techniques.
Winterlight Labs, Research Software Engineer, Sep 2017 - Sep 2018
Automatic detection of dementia from narrative speeches.
TripAdvisor, Software Engineering Intern, June - Aug, 2017
Android applications and Java API.
Dynamic Systems Lab at UTIAS, Research Assistant, May - Sep, 2016
Enhancing drone controllers using deep neural networks.

Teaching

University of Toronto, as Teaching Assistant:


Service

  • Reviewing for conferences:
    • ACL (2020, 2021)
    • EMNLP (2020)
    • NAACL (2021)
    • AAAI (2021)
  • Reviewing for journals:
    • IEEE Journal of Biomedical and Health Informatics (2020)
    • Computer Methods & Programs in Biomedicine (2018)

Awards

  • Vector Institute PhD Fellowship, 2020
  • Dean’s List, undergraduate years 2014 - 2019
  • Engineering Science Research Opportunity Program (ESROP) fellowship, 2016 summer
  • Chinese Physics Olympics (CPhO) Provincial 1st Prize, 2013

Selected Talks

  • Invited talk. Improving the neural NLP model performances with linguistic probes, Zhi-Yi Technology Advances in NLP talk, Nov 20, 2020
  • Invited talk. An information theoretic view on selecting linguistic probes, Tsinghua University AI TIME talk, Oct 30, 2020
  • Spotlight talk. Examining the rhetorical capacities of neural language models, Vector Institute NLP Symposium, Sep 16, 2020
  • Invited talk. RecitalBoard: Efficient pre-training methods for language modeling, Tencent Jarvis Lab, Shenzhen, China, Aug 5, 2019
  • Invited talk. Detecting cognitive impairments with machine learning, UTMIST, Toronto, Canada, Nov 20, 2018
  • Invited talk. Probabilistic Graphical Models, UTADA, Toronto, Canada, Oct 21, 2017

Media Coverage


Misc

<!—div>


</div->