Analyzing Semantic Change through Lexical Replacements

Francesco Periti, Pierluigi Cassotti, Haim Dubossarsky, Nina Tahmasebi


Abstract
Modern language models are capable of contextualizing words based on their surrounding context. However, this capability is often compromised due to semantic change that leads to words being used in new, unexpected contexts not encountered during pre-training. In this paper, we model semantic change by studying the effect of unexpected contexts introduced by lexical replacements. We propose a replacement schema where a target word is substituted with lexical replacements of varying relatedness, thus simulating different kinds of semantic change. Furthermore, we leverage the replacement schema as a basis for a novel interpretable model for semantic change. We are also the first to evaluate the use of LLaMa for semantic change detection.
Anthology ID:
2024.acl-long.246
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4495–4510
Language:
URL:
https://aclanthology.org/2024.acl-long.246
DOI:
Bibkey:
Cite (ACL):
Francesco Periti, Pierluigi Cassotti, Haim Dubossarsky, and Nina Tahmasebi. 2024. Analyzing Semantic Change through Lexical Replacements. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4495–4510, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Analyzing Semantic Change through Lexical Replacements (Periti et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.246.pdf