Abstract
Measuring semantic change has thus far remained a task where methods using contextual embeddings have struggled to improve upon simpler techniques relying only on static word vectors. Moreover, many of the previously proposed approaches suffer from downsides related to scalability and ease of interpretation. We present a simplified approach to measuring semantic change using contextual embeddings, relying only on the most probable substitutes for masked terms. Not only is this approach directly interpretable, it is also far more efficient in terms of storage, achieves superior average performance across the most frequently cited datasets for this task, and allows for more nuanced investigation of change than is possible with static word vectors.- Anthology ID:
- 2023.acl-short.52
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 590–602
- Language:
- URL:
- https://aclanthology.org/2023.acl-short.52
- DOI:
- 10.18653/v1/2023.acl-short.52
- Cite (ACL):
- Dallas Card. 2023. Substitution-based Semantic Change Detection using Contextual Embeddings. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 590–602, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Substitution-based Semantic Change Detection using Contextual Embeddings (Card, ACL 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.acl-short.52.pdf