On Romanization for Model Transfer Between Scripts in Neural Machine Translation

Chantal Amrhein, Rico Sennrich


Abstract
Transfer learning is a popular strategy to improve the quality of low-resource machine translation. For an optimal transfer of the embedding layer, the child and parent model should share a substantial part of the vocabulary. This is not the case when transferring to languages with a different script. We explore the benefit of romanization in this scenario. Our results show that romanization entails information loss and is thus not always superior to simpler vocabulary transfer methods, but can improve the transfer between related languages with different scripts. We compare two romanization tools and find that they exhibit different degrees of information loss, which affects translation quality. Finally, we extend romanization to the target side, showing that this can be a successful strategy when coupled with a simple deromanization model.
Anthology ID:
2020.findings-emnlp.223
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2461–2469
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.223
DOI:
10.18653/v1/2020.findings-emnlp.223
Bibkey:
Cite (ACL):
Chantal Amrhein and Rico Sennrich. 2020. On Romanization for Model Transfer Between Scripts in Neural Machine Translation. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2461–2469, Online. Association for Computational Linguistics.
Cite (Informal):
On Romanization for Model Transfer Between Scripts in Neural Machine Translation (Amrhein & Sennrich, Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2020.findings-emnlp.223.pdf
Data
OPUS-100