Improving Multilingual Neural Machine Translation with Auxiliary Source Languages

Weijia Xu, Yuwei Yin, Shuming Ma, Dongdong Zhang, Haoyang Huang


Abstract
Multilingual neural machine translation models typically handle one source language at a time. However, prior work has shown that translating from multiple source languages improves translation quality. Different from existing approaches on multi-source translation that are limited to the test scenario where parallel source sentences from multiple languages are available at inference time, we propose to improve multilingual translation in a more common scenario by exploiting synthetic source sentences from auxiliary languages. We train our model on synthetic multi-source corpora and apply random masking to enable flexible inference with single-source or bi-source inputs. Extensive experiments on Chinese/English-Japanese and a large-scale multilingual translation benchmark show that our model outperforms the multilingual baseline significantly by up to +4.0 BLEU with the largest improvements on low-resource or distant language pairs.
Anthology ID:
2021.findings-emnlp.260
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venues:
EMNLP | Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3029–3041
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.260
DOI:
10.18653/v1/2021.findings-emnlp.260
Bibkey:
Cite (ACL):
Weijia Xu, Yuwei Yin, Shuming Ma, Dongdong Zhang, and Haoyang Huang. 2021. Improving Multilingual Neural Machine Translation with Auxiliary Source Languages. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3029–3041, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Improving Multilingual Neural Machine Translation with Auxiliary Source Languages (Xu et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.260.pdf
Data
ASPEC