Abstract
Multilingual Machine Translation (MMT) benefits from knowledge transfer across different language pairs. However, improvements in one-to-many translation compared to many-to-one translation are only marginal and sometimes even negligible. This performance discrepancy raises the question of to what extent positive transfer plays a role on the target-side for one-to-many MT. In this paper, we conduct a large-scale study that varies the auxiliary target-side languages along two dimensions, i.e., linguistic similarity and corpus size, to show the dynamic impact of knowledge transfer on the main language pairs. We show that linguistically similar auxiliary target languages exhibit strong ability to transfer positive knowledge. With an increasing size of similar target languages, the positive transfer is further enhanced to benefit the main language pairs. Meanwhile, we find distant auxiliary target languages can also unexpectedly benefit main language pairs, even with minimal positive transfer ability. Apart from transfer, we show distant auxiliary target languages can act as a regularizer to benefit translation performance by enhancing the generalization and model inference calibration.- Anthology ID:
- 2024.eacl-long.110
- Volume:
- Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- March
- Year:
- 2024
- Address:
- St. Julian’s, Malta
- Editors:
- Yvette Graham, Matthew Purver
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1828–1840
- Language:
- URL:
- https://aclanthology.org/2024.eacl-long.110
- DOI:
- Cite (ACL):
- Yan Meng and Christof Monz. 2024. Disentangling the Roles of Target-side Transfer and Regularization in Multilingual Machine Translation. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1828–1840, St. Julian’s, Malta. Association for Computational Linguistics.
- Cite (Informal):
- Disentangling the Roles of Target-side Transfer and Regularization in Multilingual Machine Translation (Meng & Monz, EACL 2024)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2024.eacl-long.110.pdf