Yi (Jodie) Zhou

Yi (Jodie) Zhou

Postdoctoral Research Associate @ Cardiff NLP Group

I am a Lecturer (Assistant Professor) in the School of Computer Science and Informatics at Cardiff University. Prior to this, I was a Postdoc at the NLP group at Cardiff University. Before, I was a Ph.D. student in Natural Language Processing (a branch of AI) at the Computer Science department at the University of Liverpool, advised by Prof. Danushka Bollegala and Dr. Shan Luo. Previously, I received my MSc in Big Data and High Performance Computing at the University of Liverpool.

My research mainly focuses on lexical semantics and responsible AI, such as ethics, bias and fairness in NLP. My research interests are broadly in natural language understanding, such as language representation learning, multimodality, commonsense reasoning, multiliguility approaches, text generation, interpretability and analysis of models.

🔥 News

  • 20/09/2024:  🎉🎉 One paper is accepted at EMNLP 2024 main conference.
  • 01/06/2024:  👩‍💻👩‍💻 I started working as a Lecturer (Assistant Professor) at Cardiff University.
  • 20/02/2024:  🎉🎉 One paper is accepted at LREC-Coling 2024 main conference.
  • 07/10/2023:  🎉🎉 Three papers are accepted to EMNLP 2023 main conference/Findings.
  • 02/08/2023:  👩‍💻👩‍💻 Visiting researcher at Users & Information Lab at Korea Advanced Institute of Science & Technology (KAIST).
  • 01/05/2023:  🎉🎉 One paper is accepted at ACL 2023 main conference.
  • 01/05/2023:  🎉🎉 Two papers are accepted at Findings of ACL 2023.
  • 01/02/2023:  👩‍💻👩‍💻 I started working as a postdoctoral researcher at Professor Jose Camacho-Collados’s group at Cardiff University.
  • 06/10/2022:  🎉🎉 One paper is accepted at Findings of EMNLP 2022.
  • 24/02/2022:  🎉🎉 One paper is accepted at ACL 2022 main conference.

📝 Publications

  • Yi Zhou, Danushka Bollegala and Jose Camacho-Collados: Evaluating Short-Term Temporal Fluctuations of Social Biases in Social Media Data and Masked Language Models, Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), November 2024.
  • Gaifan Zhan, Yi Zhou and Danushka Bollegala: Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-Coling), May 2024.
  • Yi Zhou, Jose Camacho Collados, and Danushka Bollegala: A Predictive Factor Analysis of Social Biases and Task-Performance in Pre-trained Masked Language Models, Proceedings of the Empirical Methods in Natural Language Processing (EMNLP), December 2023.
  • Asahi Ushio, Yi Zhou, Jose Camacho-Collados: An Efficient Multilingual Language Model Compression through Vocabulary Trimming, Proceedings of the Findings Empirical Methods in Natural Language Processing (Findings of EMNLP), December 2023.
  • Xiaohang Tang, Yi Zhou, Taichi Aida, Procheta Sen and Danushka Bollegala: Can Word Sense Distribution Detect Semantic Changes of Words?, Proceedings of the Findings Empirical Methods in Natural Language Processing (Findings of EMNLP), December 2023.
  • Xiaohang Tang, Yi Zhou, Danushka Bollegala: Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023), Toronto, Canada, July 2023.
  • Saeth Wannasuphoprasit, Yi Zhou, Danushka Bollegala: Solving Cosine Similarity Underestimation between High-Frequency Words by L2 Norm Discounting. In Findings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023), Toronto, Canada, July 2023.
  • Haochen Luo, Yi Zhou and Danushka Bollegala: Together We Make Sense–Learning Meta-Sense Embeddings, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Findings of ACL 2023), Toronto, Canada, July, 2023.
  • Yi Zhou, Danushka Bollegala: On the Curious Case of ℓ2 norm of Sense Embeddings. In Findings of the Empirical Methods in Natural Language Processing (EMNLP 2022), Abu Dhabi, December 2022.
  • Yi Zhou, Masahiro Kaneko, Danushka Bollegala: Sense Embeddings are also Biased – Evaluating Social Biases in Static and Contextualised Sense Embeddings. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022), Dublin, Ireland, 2022.

👩‍🔬 Research Experience

🎖️ Awards

  • University of Liverpool Graduate Association Hong Kong and Tung Scholarships. University of Liverpool, UK, 2021-2022.
  • Second Place Dongfeng Scholarship, Hubei University of Automotive Technology, China, 2013.
  • Third Place People’s Public Fund Scholarship, Hubei University of Automotive Technology, China, 2011-2012.
  • Third Place People’s Public Fund Scholarship, Hubei University of Automotive Technology, China, 2010-2011.

💬 Invited Talks

  • Sep.2023, Social Bias in Masked Language Models and Embeddings, Cardiff NLP Seminar, Cardiff NLP Seminar, Cardiff University
  • Aug.2023, Social Bias in Masked Language Models and Embeddings, NLP/Ethics Seminar, KAIST
  • Jul.2023, Social Bias in Masked Language Models and Embeddings. NLP Group, UCL
  • Mar.2023, Representation Learning for Word Senses and Evaluation of Their Properties, Cardiff NLP Seminar, Cardiff University
  • Jun.2021, Sense embeddings Learning Using Contextualised and Static Word Embeddings, ML Group, University of Liverpool
  • May.2019, Sense embeddings Learning Using Contextualised and Static Word Embeddings, Research Student Talks, University of Liverpool

Feel free to drop me an email if you’d like me to give a talk at your event/seminar.

👩‍🏫 Teaching

University of Liverpool

  • Teaching Assistant, Data mining and visualization (masters level) (2021/2022)
  • Teaching Assistant, Machine Learning and Bioinspired Optimisation (masters level) (2020/2021)
  • Teaching Assistant, Applied Artificial Intelligence (masters level) (2020/2021)
  • Teaching Assistant, App Development (2020/2021, 2019/2020, 2018/2019)
  • Teaching Assistant, Software Engineering (2020/2021, 2019/2020)
  • Teaching Assistant, Object-Oriented Programming (2019/2020)
  • Teaching Assistant, Computer Systems (2018/2019)
  • Teaching Assistant, Mobile Computing (2018/2019)
  • Teaching Assistant, Database Development (2018/2019)

📚 Student Mentoring

University of Liverpool

  • Xiaohang Tang, BS student at the University of Liverpool (2022), now a PhD student at Virginia Polytechnic Institute and State University (Co-advise with Prof. Danushka Bollegala)
  • Gaifan Zhang, BS student at the University of Liverpool (2022), now an MS student at Columbia University in the City of New York (Co-advise with Prof. Danushka Bollegala)
  • Saeth Wannasuphoprasit, MS student at the University of Liverpool (2022), now a Data Scientist at Volkswagen Group of America, Innovation and Engineering Center California (IECC) (Co-advise with Prof. Danushka Bollegala)
  • Haochen Luo, BS student at the University of Liverpool (2021), MS student at Oxford University (Co-advise with Prof. Danushka Bollegala)

💻 Professional Services

Tutorial Instructor

  • Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation (Data challenge ICWSM 2023)

Workshop Co-organizer

  • 2nd Cardiff NLP Summer Workshop

Senior Member

  • Area Chair/Action Editors: ACL (2024-), EMMLP (2024-), EACL (2024-), NAACL (2024-), COLING (2024-), ACL Rolling Review (2023-)
  • Publicity Chair: *SEM 2024

Reviewer/Program Committee

  • Conference: EMNLP (2023-), ACL (2023-), EACL (2022-), ACL Rolling Review (ARR) (2021-), *SEM (2023)
  • Journal: Natural Language Processing (2024), Information Processing and Management (2023), International Journal of Data Science and Analytics (2023)