Abstract
Automatically highlighting words that cause semantic differences between two documents could be useful for a wide range of applications. We formulate recognizing semantic differences (RSD) as a token-level regression task and study three unsupervised approaches that rely on a masked language model. To assess the approaches, we begin with basic English sentences and gradually move to more complex, cross-lingual document pairs. Our results show that an approach based on word alignment and sentence-level contrastive learning has a robust correlation to gold labels. However, all unsupervised approaches still leave a large margin of improvement.- Anthology ID:
- 2023.emnlp-main.835
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13543–13552
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.835
- DOI:
- 10.18653/v1/2023.emnlp-main.835
- Cite (ACL):
- Jannis Vamvas and Rico Sennrich. 2023. Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13543–13552, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents (Vamvas & Sennrich, EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.emnlp-main.835.pdf