Multilingual Representation Distillation with Contrastive Learning
Abstract
Multilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and matching tasks. In this paper, we integrate contrastive learning into multilingual representation distillation and use it for quality estimation of parallel sentences (i.e., find semantically similar sentences that can be used as translations of each other). We validate our approach with multilingual similarity search and corpus filtering tasks. Experiments across different low-resource languages show that our method greatly outperforms previous sentence encoders such as LASER, LASER3, and LaBSE.- Anthology ID:
- 2023.eacl-main.108
- Volume:
- Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Andreas Vlachos, Isabelle Augenstein
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1477–1490
- Language:
- URL:
- https://aclanthology.org/2023.eacl-main.108
- DOI:
- 10.18653/v1/2023.eacl-main.108
- Cite (ACL):
- Weiting Tan, Kevin Heffernan, Holger Schwenk, and Philipp Koehn. 2023. Multilingual Representation Distillation with Contrastive Learning. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1477–1490, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Multilingual Representation Distillation with Contrastive Learning (Tan et al., EACL 2023)
- PDF:
- https://preview.aclanthology.org/teach-a-man-to-fish/2023.eacl-main.108.pdf