Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910317622067200 |
|---|---|
| author | Meng, Yan Monz, Christof |
| author_facet | Meng, Yan Monz, Christof |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01772 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translation Meng, Yan Monz, Christof Computation and Language Artificial Intelligence Machine Learning 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. |
| title | Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translation |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2402.01772 |