Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation

Hongyuan Lu, Haoyang Huang, Dongdong Zhang, Furu Wei, Wai Lam

Abstract
Despite the fact that multilingual agreement (MA) has shown its importance for multilingual neural machine translation (MNMT), current methodologies in the field have two shortages: (i) require parallel data between multiple language pairs, which is not always realistic and (ii) optimize the agreement in an ambiguous direction, which hampers the translation performance. We present Bidirectional Multilingual Agreement via Switched Back-translation (BMA-SBT), a novel and universal multilingual agreement framework for fine-tuning pre-trained MNMT models, which (i) exempts the need for aforementioned parallel data by using a novel method called switched BT that creates synthetic text written in another source language using the translation target and (ii) optimizes the agreement bidirectionally with the Kullback-Leibler Divergence loss. Experiments indicate that BMA-SBT clearly improves the strong baselines on the task of MNMT with three benchmarks: TED Talks, News, and Europarl. In-depth analyzes indicate that BMA-SBT brings additive improvements to the conventional BT method.
Anthology ID:
2024.findings-eacl.19
Volume:
Findings of the Association for Computational Linguistics: EACL 2024
Month:
March
Year:
2024
Address:
St. Julian’s, Malta
Editors:
Yvette Graham, Matthew Purver
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
264–275
Language:
URL:
https://aclanthology.org/2024.findings-eacl.19
DOI:
Bibkey:
Cite (ACL):
Hongyuan Lu, Haoyang Huang, Dongdong Zhang, Furu Wei, and Wai Lam. 2024. Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation. In Findings of the Association for Computational Linguistics: EACL 2024, pages 264–275, St. Julian’s, Malta. Association for Computational Linguistics.
Cite (Informal):
Revamping Multilingual Agreement Bidirectionally via Switched Back-translation for Multilingual Neural Machine Translation (Lu et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2024.findings-eacl.19.pdf
PDF Search