Sahrish Khan

Sahrish Khan is a PhD student funded by the Computer Science Departmental Scholarship. She is under the supervision of Dr. Gabriele Pergola , Dr Arshad Jhumka and Dr. Sara Kalvala . Her primary research interests lie in Natural Language Processing, with a focus on Sexism Detection and Fine-Grained Text Classification.

Teaching Assistant

Sahrish has worked as a TA in the following module:

• CS349: Principles of Programming LanguagesLink opens in a new window (2022/23, 2023/24, 2024/25)
• CS133: Professional Skills (2022/23, 2023/24, 2024/25)
• CS118: Programming for Computer Scientists (2023/24)
• CS132: Computer Organisation and ArchitectureLink opens in a new window (2023/24)
• CS2D1-30: Software Engineering (2022/23, 2023/24)
• CS141: Functional Programming (2022/23)

Research Assistant

Sahrish has worked as a RA in the following project:

• Development of an NLP model to detect threatening and abusive language used in communication with victims (2023/24 - NPCC Forensic Capability Network)

  • On the News: AI that detects hate messages against women could also be turned on drug dealers | The Independent | Link opens in a new windowLink opens in a new windowDaily Mail | Link opens in a new windowLink opens in a new windowThe Standard | Link opens in a new windowLink opens in a new windowMSN | Link opens in a new windowLink opens in a new windowFCN (2024) | Link opens in a new windowLink opens in a new windowFCN (2023)Link opens in a new window

Publications

• Sahrish Khan, Arshad Jhumka, and Gabriele Pergola. Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detection. The 2025 Annual Meeting of the Association for Computational Linguistics (ACL), 2025.

• Xingwei Tan, Chen Lyu, Hafiz M. Umer, Sahrish Khan, Meenatchi Parvatham, Lois Arthurs, Simon Cullen, Shelley Wilson, Arshad Jhumka, and Gabriele Pergola. SafeSpeech: A Comprehensive and Interactive Tool for Analysing Sexist and Abusive Language in Conversations. The North American Chapter of the Association for Computational Linguistics: Human Language Technologies – System Demonstrations (NAACL), 2025,

• S. Khan, G. Pergola, A. Jhumka. Multilingual Sexism Identification via Fusion of Large Language ModelsLink opens in a new window. In Working Notes of CLEF 2024 - Conference and Labs of the Evaluation Forum (CLEF), 2024. Note: Our two models ranked 1^st and 2^nd for Task 1 in the English segment (Team: EquityExplorer).

• S. Khan, R.A. Abbasi, M.A. Sindhu et al.Predicting the victims of hate speech on microblogging platforms

Contact

Email: sahrish.khan@warwick.ac.uk