Dr Cass Zhixue Zhao
School of Computer Science
Lecturer in Natural Language Processing
zhixue.zhao@sheffield.ac.uk
Regent Court (DCS)
Full contact details
Dr Cass Zhixue Zhao
School of Computer Science
Regent Court (DCS)
211 Portobello
Sheffield
S1 4DP
School of Computer Science
Regent Court (DCS)
211 Portobello
Sheffield
S1 4DP
- Profile
-
Cass (Zhixue) Zhao is a lecturer in Natural Language Processing in the Department of Computer Science at the University of Sheffield. Before that she was a postdoc researcher, supervised by Prof Nikos Aletras, on model interpretability, model hallucination and model compression. Back in 2020 she worked as a research assistant within the same department, working on NIHR-funded NLP projects for systematic reviews of public health research. She has served on the Programme Committee for AAAI, ACL and EMNLP. She is currently looking for highly-motivated PhD students, please contact her directly if you are interested.
- Research interests
-
- Model explanation
- Model compression
- Model bias and hallucination
- Model reasoning
- Publications
-
Journal articles
- Utilizing subjectivity level to mitigate identity term bias in toxic comments classification. Online Social Networks and Media, 29, 100205-100205.
Conference proceedings papers
- A Comparative Study of Using Pre-trained Language Models for Toxic Comment Classification. Companion Proceedings of the Web Conference 2021 View this article in WRRO
Preprints
- Incorporating Attribution Importance for Improving Faithfulness Metrics, arXiv.
- On the Impact of Temporal Concept Drift on Model Explanations, arXiv.
- SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of "Subjectivity" and "Identity Terms", arXiv.
- Utilizing subjectivity level to mitigate identity term bias in toxic comments classification. Online Social Networks and Media, 29, 100205-100205.
- Research group
-
Natural Language Processing