Abstract
In this paper, we investigate automatic detection of subtle semantic shifts between social communities of different political convictions in Dutch and English. We perform a methodological study comparing methods using static and contextualized language models. We investigate the impact of specializing contextualized models through fine-tuning on target corpora, word sense disambiguation and sentiment. We furthermore propose a new approach using masked token prediction, that relies on behavioral information, specifically the most probable substitutions, instead of geometrical comparison of representations. Our results show that methods using static models and our masked token prediction method can detect differences in connotation of politically loaded terms, whereas methods that rely on measuring the distance between contextualized representations are not providing clear signals, even in synthetic scenarios of extreme shifts.- Anthology ID:
- 2023.findings-emnlp.237
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3662–3675
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.237
- DOI:
- 10.18653/v1/2023.findings-emnlp.237
- Cite (ACL):
- Sanne Hoeken, Özge Alacam, Antske Fokkens, and Pia Sommerauer. 2023. Methodological Insights in Detecting Subtle Semantic Shifts with Contextualized and Static Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3662–3675, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Methodological Insights in Detecting Subtle Semantic Shifts with Contextualized and Static Language Models (Hoeken et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.findings-emnlp.237.pdf