Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval
John Wieting, Jonathan Clark, William Cohen, Graham Neubig, Taylor Berg-Kirkpatrick
Abstract
Contrastive learning has been successfully used for retrieval of semantically aligned sentences, but it often requires large batch sizes or careful engineering to work well. In this paper, we instead propose a generative model for learning multilingual text embeddings which can be used to retrieve or score sentence pairs. Our model operates on parallel data in N languages and, through an approximation we introduce, efficiently encourages source separation in this multilingual setting, separating semantic information that is shared between translations from stylistic or language-specific variation. We show careful large-scale comparisons between contrastive and generation-based approaches for learning multilingual text embeddings, a comparison that has not been done to the best of our knowledge despite the popularity of these approaches. We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval - the last of which we introduce in this paper. Overall, our model outperforms both a strong contrastive and generative baseline on these tasks.- Anthology ID:
- 2023.acl-long.673
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long 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:
- 12044–12066
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.673
- DOI:
- 10.18653/v1/2023.acl-long.673
- Cite (ACL):
- John Wieting, Jonathan Clark, William Cohen, Graham Neubig, and Taylor Berg-Kirkpatrick. 2023. Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12044–12066, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval (Wieting et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2023.acl-long.673.pdf