![Usashi Chatterjee](https://profiles-cardiff.imgix.net/attachments/1558?w=200&h=200&auto=format&crop=faces&fit=crop&q=90")
Dr Usashi Chatterjee
(she/her)
Lecturer
School of Computer Science and Informatics
- ChatterjeeU@cardiff.ac.uk
- +44 29225 14922
- Abacws, Room Room 2.58, Senghennydd Road, Cathays, Cardiff, CF24 4AG
Overview
I am a Lecturer in Computer Science and Informatics at the Cardiff University, UK. I teach both undergraduate and postgraduate modules. My main areas of research lies in Semantic Web, Knowledge Representation and Reuse. Presently, my research work focuses on developing strategies for using large language models (LLMs) explictly and implicitly for multiple concept embeddings.
I have also been an active participant in other projects with the KnowDive Group, University of Trento.
My Ph.D was in Ontology Modelling - a formal ontology for facet discovery and knowledge representation. I proposed a method to build core ontology comprising a small set of concepts, it would save a lot of time and expense of the domain developers interested in building application ontologies.
Publication
2023
- Chatterjee, U. and Schockaert, S. 2023. Probing the conceptual space of ChatGPT and GPT-4. Presented at: 9th Workshop on Artificial Intelligence and Cognition, Bremen, 14-15 September 2023.
- Gajbhiye, A., Bouraoui, Z., Li, N., Chatterjee, U., Espinosa-Anke, L. and Schockaert, S. 2023. What do deck chairs and sun hats have in common? Uncovering shared properties in large concept vocabularies. Presented at: Conference on Empirical Methods in Natural Language Processing, EMNLP, Singapore, 6-10 December 2023 Presented at Bouamor, H., Pino, J. and Bali, K. eds.Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics pp. 10587–10596., (10.18653/v1/2023.emnlp-main.654)
- Chatterjee, U., Gajbhiye, A. and Schockaert, S. 2023. Cabbage sweeter than cake? Analysing the potential of large language models for learning conceptual spaces. Presented at: Conference on Empirical Methods in Natural Language Processing, EMNLP, Singapore, 6-10 December 2023 Presented at Bouamor, H., Pino, J. and Bali, K. eds.Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics pp. 11836–11842., (10.18653/v1/2023.emnlp-main.725)
2021
- Chatterjee, U. 2021. Context-based understanding of food-related queries using a culinary knowledge model. Journal of Information Science 49(3), pp. 831-852. (10.1177/01655515211022163)
2020
- Loizides, F. et al. eds. 2020. Human computer interaction and emerging technologies. Cardiff: Cardiff University Press. (10.18573/book3)
Articles
- Chatterjee, U. 2021. Context-based understanding of food-related queries using a culinary knowledge model. Journal of Information Science 49(3), pp. 831-852. (10.1177/01655515211022163)
Books
- Loizides, F. et al. eds. 2020. Human computer interaction and emerging technologies. Cardiff: Cardiff University Press. (10.18573/book3)
Conferences
- Chatterjee, U. and Schockaert, S. 2023. Probing the conceptual space of ChatGPT and GPT-4. Presented at: 9th Workshop on Artificial Intelligence and Cognition, Bremen, 14-15 September 2023.
- Gajbhiye, A., Bouraoui, Z., Li, N., Chatterjee, U., Espinosa-Anke, L. and Schockaert, S. 2023. What do deck chairs and sun hats have in common? Uncovering shared properties in large concept vocabularies. Presented at: Conference on Empirical Methods in Natural Language Processing, EMNLP, Singapore, 6-10 December 2023 Presented at Bouamor, H., Pino, J. and Bali, K. eds.Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics pp. 10587–10596., (10.18653/v1/2023.emnlp-main.654)
- Chatterjee, U., Gajbhiye, A. and Schockaert, S. 2023. Cabbage sweeter than cake? Analysing the potential of large language models for learning conceptual spaces. Presented at: Conference on Empirical Methods in Natural Language Processing, EMNLP, Singapore, 6-10 December 2023 Presented at Bouamor, H., Pino, J. and Bali, K. eds.Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics pp. 11836–11842., (10.18653/v1/2023.emnlp-main.725)
Research
My research interest lies in knowledge representation and reuse. Knowledge needs systematic and scientific representation for efficient organization, interpretation and reuse.
Currently, I am working on three different research projects.
- Explore Large Language Models (LLMs) such as ChatGPT and GPT-4 for knowledge extraction.
- Learn concept representations, investigate multiple concept embeddings for imporving multi-label classification.
- Build a comprehensive and easily accessible global farm-to-fork ontology about food and agriculture.
Teaching
I am module leader for the following modules:
- CMT313 Software Engineering, which is a dual semester module taught in MSc Computing programme.
- CM6125/CM6625 Database Systems, which is a spring semester module taught in 1st Year of the Applied Software Engineering programme.
I am also a Year Tutor for 2nd Year Applied Software Engineering (ASE).
Biography
- Lecturer, Cardiff University, 2021 - Present
- Teacher, Cardiff University, 2020 - 2021
- Teaching Associate, Cardiff University, 2018 - 2020
- Visiting Research Fellow, University of Trento, 2014 - 2019
- PhD in Semantic Web, Indian Statistical Institute (2018)
Honours and awards
Fellowship, Higher Education Academy (2022)
National Eligibility Test for Lectureship (2013)