Solving hard analogy questions with relation embedding chains

Kumar, Nitesh and Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 2023. Solving hard analogy questions with relation embedding chains. 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, 6224–6236. 10.18653/v1/2023.emnlp-main.382

Preview

PDF - Accepted Post-Print Version Download (421kB) | Preview

Abstract

Modelling how concepts are related is a central topic in Lexical Semantics. A common strategy is to rely on knowledge graphs (KGs) such as ConceptNet, and to model the relation between two concepts as a set of paths. However, KGs are limited to a fixed set of relation types, and they are incomplete and often noisy. Another strategy is to distill relation embeddings from a fine-tuned language model. However, this is less suitable for words that are only indirectly related and it does not readily allow us to incorporate structured domain knowledge. In this paper, we aim to combine the best of both worlds. We model relations as paths but associate their edges with relation embeddings. The paths are obtained by first identifying suitable intermediate words and then selecting those words for which informative relation embeddings can be obtained. We empirically show that our proposed representations are useful for solving hard analogy questions.

Item Type:	Conference or Workshop Item (Paper)
Status:	Published
Schools:	Advanced Research Computing @ Cardiff (ARCCA) Computer Science & Informatics
Publisher:	Association for Computational Linguistics
Date of First Compliant Deposit:	13 February 2024
Date of Acceptance:	7 October 2023
Last Modified:	10 Jun 2024 09:05
URI:	https://orca.cardiff.ac.uk/id/eprint/165644

Actions (repository staff only)

Edit Item