![Hsuvas Borkakoty](https://profiles-cardiff.imgix.net/attachments/7250?w=200&h=200&auto=format&crop=faces&fit=crop&q=90")
Mr Hsuvas Borkakoty
(he/him)
Teams and roles for Hsuvas Borkakoty
Graduate Demonstrator
Research student
Overview
I am a PhD student under the Supervision of Dr. Luis Espinosa-Anke. My area of research is to understand how Wikipedia can attribute to detect temporal changes in NLP, as well as how we can use NLP to improve content reliability of Wikipedia.
Publication
2025
- Borkakoty, H. and Espinosa-Anke, L. 2025. TACTICAL: A framework for building Wikipedia-derived timelines of atomic changes. Presented at: 28th European Conference on Artificial Intelligence Bologna, Italy 25-30 October 2025. Published in: Lynce, I. et al., ECAI 2025. Frontiers in Artificial Intelligence and Applications IOS Press. , pp.4410-4417. (10.3233/faia251339)
- Borkakoty, H. and Espinosa-Anke, L. 2025. WiDe-Analysis: enabling one-click content moderation analysis on Wikipedia’s articles for deletion. Presented at: ECAI 2025 Workshop on Intelligent Management Information Systems (IMIS 2025) Bologna, Italy 25-30 10 2025. Published in: Hernes, M. , Walaszczyk, E. and Rot, A. eds. Emerging Challenges in Intelligent Management Information Systems: Proceedings of 28th European Conference on Artificial Intelligence ECAI 2025 - IMIS Workshop, Volume 2. Vol. 2.Chem: Springer. , pp.351-365. (10.1007/978-3-032-06611-4_27)
2024
- Borkakoty, H. and Espinosa-Anke, L. 2024. HOAXPEDIA: A unified Wikipedia hoax articles dataset. Presented at: 2024 Conference on Empirical Methods in Natural Language Processing Miami, Florida 12-16 November 2024. Published in: Lucie-Aimée, L. et al., Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia. Association for Computational Linguistics. , pp.53–66.
- Myung, J. et al., 2024. BLEND: A benchmark for LLMs on everyday knowledge in diverse cultures and languages. Presented at: 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks Vancouver, BC, Canada 9-15 December 2024. Published in: Globerson, A. et al., NeurIPS Proceedings: Advances in Neural Information Processing Systems. Vol. 37.Curran Associates, Inc.. , pp.78104-78146.
2023
- Borkakoty, H. and Espinosa-Anke, L. 2023. WIKITIDE: A Wikipedia-based timestamped definition pairs dataset. Presented at: R A N L P 2 0 2 3 International conference recent advances in natural language processing 4-6 September 2023. Proceedings of Recent Advances in Natural Language Processing. Shoumen, Bulgaria: INCOMA Ltd. , pp.207-216. (10.26615/978-954-452-092-2_023)
Conferences
- Borkakoty, H. and Espinosa-Anke, L. 2024. HOAXPEDIA: A unified Wikipedia hoax articles dataset. Presented at: 2024 Conference on Empirical Methods in Natural Language Processing Miami, Florida 12-16 November 2024. Published in: Lucie-Aimée, L. et al., Proceedings of the First Workshop on Advancing Natural Language Processing for Wikipedia. Association for Computational Linguistics. , pp.53–66.
- Borkakoty, H. and Espinosa-Anke, L. 2025. TACTICAL: A framework for building Wikipedia-derived timelines of atomic changes. Presented at: 28th European Conference on Artificial Intelligence Bologna, Italy 25-30 October 2025. Published in: Lynce, I. et al., ECAI 2025. Frontiers in Artificial Intelligence and Applications IOS Press. , pp.4410-4417. (10.3233/faia251339)
- Borkakoty, H. and Espinosa-Anke, L. 2025. WiDe-Analysis: enabling one-click content moderation analysis on Wikipedia’s articles for deletion. Presented at: ECAI 2025 Workshop on Intelligent Management Information Systems (IMIS 2025) Bologna, Italy 25-30 10 2025. Published in: Hernes, M. , Walaszczyk, E. and Rot, A. eds. Emerging Challenges in Intelligent Management Information Systems: Proceedings of 28th European Conference on Artificial Intelligence ECAI 2025 - IMIS Workshop, Volume 2. Vol. 2.Chem: Springer. , pp.351-365. (10.1007/978-3-032-06611-4_27)
- Borkakoty, H. and Espinosa-Anke, L. 2023. WIKITIDE: A Wikipedia-based timestamped definition pairs dataset. Presented at: R A N L P 2 0 2 3 International conference recent advances in natural language processing 4-6 September 2023. Proceedings of Recent Advances in Natural Language Processing. Shoumen, Bulgaria: INCOMA Ltd. , pp.207-216. (10.26615/978-954-452-092-2_023)
- Myung, J. et al., 2024. BLEND: A benchmark for LLMs on everyday knowledge in diverse cultures and languages. Presented at: 38th Conference on Neural Information Processing Systems (NeurIPS 2024) Track on Datasets and Benchmarks Vancouver, BC, Canada 9-15 December 2024. Published in: Globerson, A. et al., NeurIPS Proceedings: Advances in Neural Information Processing Systems. Vol. 37.Curran Associates, Inc.. , pp.78104-78146.
Research
My topic of research is to study Wikipedia as a temporal data source for Large Language Models and to study Large Language Models for content moderation in Wikipedia. Apart from my topic, I have also collaborated with my peers in CardiffNLP group as well as peers from different universities on topics such as Understanding metaphors and analogies, Developing Cultural Benchmark for LLMs, and Detection of temporal change in Social Media data.
Teaching
CMT307 (PGR Demonstrator): Applied Machine Learning
CMT316 (PGR Demonstrator): Applied Machine Learning- Computer Vision and Natural Language Processing
CM2307 (PGR Demonstrator): Algorithms and Data Structure