![Usashi Chatterjee](https://profiles-cardiff.imgix.net/attachments/1558?w=200&h=200&auto=format&crop=faces&fit=crop&q=90")
Dr Usashi Chatterjee
(Mae hi'n)
Darlithydd
Yr Ysgol Cyfrifiadureg a Gwybodeg
- ChatterjeeU@caerdydd.ac.uk
- +44 29225 14922
- Abacws, Ystafell Ystafell 2.58, Ffordd Senghennydd, Cathays, Caerdydd, CF24 4AG
Trosolwyg
Rwy'n Ddarlithydd mewn Cyfrifiadureg a Gwybodeg ym Mhrifysgol Caerdydd, y DU. Rwy'n addysgu modiwlau israddedig ac ôl-raddedig. Mae fy mhrif feysydd ymchwil yn gorwedd yn Semantic Web, Knowledge Representation and Reuse. Ar hyn o bryd, mae fy ngwaith ymchwil yn canolbwyntio ar ddatblygu strategaethau ar gyfer defnyddio modelau iaith mawr (LLM) yn benodol ac yn ymhlyg ar gyfer ymgorffori cysyniadau lluosog.
Rwyf hefyd wedi bod yn gyfranogwr gweithredol mewn prosiectau eraill gyda'r KnowDive Group, Prifysgol Trento.
Roedd fy PhD mewn Modelu Ontoleg - ontoleg ffurfiol ar gyfer darganfod agweddau a chynrychiolaeth gwybodaeth. Cynigiais ddull i adeiladu ontoleg graidd sy'n cynnwys set fach o gysyniadau, byddai'n arbed llawer o amser a chost y datblygwyr parth sydd â diddordeb mewn adeiladu ontolegau cais.
Cyhoeddiad
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)
Cynadleddau
- 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)
Erthyglau
- 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)
Llyfrau
- Loizides, F. et al. eds. 2020. Human computer interaction and emerging technologies. Cardiff: Cardiff University Press. (10.18573/book3)
Ymchwil
Mae fy niddordeb ymchwil yn ymwneud â chynrychioli ac ailddefnyddio gwybodaeth. Mae angen cynrychiolaeth systematig a gwyddonol ar wybodaeth ar gyfer trefnu, dehongli ac ailddefnyddio effeithlon.
Ar hyn o bryd, rydw i'n gweithio ar dri phrosiect ymchwil gwahanol.
- Archwiliwch Fodelau Iaith Mawr (LLM) fel ChatGPT a GPT-4 i gael gwybodaeth echdynnu.
- Dysgwch gynrychioliadau cysyniad, ymchwilio i wreiddiadau cysyniad lluosog ar gyfer gosod dosbarthiad aml-label.
- Adeiladu ontoleg fyd-eang gynhwysfawr a hawdd ei chyrchu byd-eang am fwyd ac amaethyddiaeth.
Addysgu
Rwy'n arweinydd modiwl ar gyfer y modiwlau canlynol:
- CMT313 Peirianneg Meddalwedd, sy'n fodiwl semester deuol a addysgir yn rhaglen MSc Cyfrifiadura.
- Systemau Cronfa Ddata CM6125 / CM6625, sy'n fodiwl semester gwanwyn a addysgir ym mlwyddyn 1af y rhaglen Peirianneg Meddalwedd Gymhwysol.
Rwyf hefyd yn Diwtor Blwyddyn ar gyfer Peirianneg Meddalwedd Gymhwysol 2il Flwyddyn (ASE).
Bywgraffiad
- Darlithydd, Prifysgol Caerdydd, 2021 - Presennol
- Athro, Prifysgol Caerdydd, 2020 - 2021
- Cydymaith Addysgu, Prifysgol Caerdydd, 2018 - 2020
- Cymrawd Ymchwil Gwadd Prifysgol Trento, 2014 - 2019
- PhD yn Semantic Web, Sefydliad Ystadegol India (2018)
Anrhydeddau a dyfarniadau
Cymrodoriaeth, Academi Addysg Uwch (2022)
Prawf Cymhwyster Cenedlaethol ar gyfer Darlithyddiaeth (2013)