Cabbage sweeter than cake? Analysing the potential of large language models for learning conceptual spaces

Chatterjee, Usashi, Gajbhiye, Amit and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 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. Published in: Bouamor, Houda, Pino, Juan and Bali, Kalika eds. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 11836–11842. 10.18653/v1/2023.emnlp-main.725

Full text not available from this repository.

Abstract

The theory of Conceptual Spaces is an influential cognitive-linguistic framework for representing the meaning of concepts. Conceptual spaces are constructed from a set of quality dimensions, which essentially correspond to primitive perceptual features (e.g. hue or size). These quality dimensions are usually learned from human judgements, which means that applications of conceptual spaces tend to be limited to narrow domains (e.g. modelling colour or taste). Encouraged by recent findings about the ability of Large Language Models (LLMs) to learn perceptually grounded representations, we explore the potential of such models for learning conceptual spaces. Our experiments show that LLMs can indeed be used for learning meaningful representations to some extent. However, we also find that fine-tuned models of the BERT family are able to match or even outperform the largest GPT-3 model, despite being 2 to 3 orders of magnitude smaller.

Item Type:	Conference or Workshop Item (Paper)
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Association for Computational Linguistics
Related URLs:	Organisation
Date of Acceptance:	7 October 2023
Last Modified:	08 Feb 2024 11:00
URI:	https://orca.cardiff.ac.uk/id/eprint/165645

Actions (repository staff only)

Edit Item