Investigating the Contextualised Word Embedding Dimensions Specified for Contextual and Temporal Semantic Changes

Taichi Aida, Danushka Bollegala


Abstract
The sense-aware contextualised word embeddings (SCWEs) encode semantic changes of words within the contextualised word embedding (CWE) spaces. Despite the superior performance of (SCWE) in contextual/temporal semantic change detection (SCD) benchmarks, it remains unclear as to how the meaning changes are encoded in the embedding space. To study this, we compare pre-trained CWEs and their fine-tuned versions on contextual and temporal semantic change benchmarks under Principal Component Analysis (PCA) and Independent Component Analysis (ICA) transformations. Our experimental results reveal (a) although there exist a smaller number of axes that are specific to semantic changes of words in the pre-trained CWE space, this information gets distributed across all dimensions when fine-tuned, and (b) in contrast to prior work studying the geometry of CWEs, we find that PCA to better represent semantic changes than ICA within the top 10% of axes. These findings encourage the development of more efficient SCD methods with a small number of SCD-aware dimensions.
Anthology ID:
2025.coling-main.95
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1413–1437
Language:
URL:
https://aclanthology.org/2025.coling-main.95/
DOI:
Bibkey:
Cite (ACL):
Taichi Aida and Danushka Bollegala. 2025. Investigating the Contextualised Word Embedding Dimensions Specified for Contextual and Temporal Semantic Changes. In Proceedings of the 31st International Conference on Computational Linguistics, pages 1413–1437, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Investigating the Contextualised Word Embedding Dimensions Specified for Contextual and Temporal Semantic Changes (Aida & Bollegala, COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.95.pdf