On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation

Liang Chen, Shuming Ma, Dongdong Zhang, Furu Wei, Baobao Chang


Abstract
While multilingual neural machine translation has achieved great success, it suffers from the off-target issue, where the translation is in the wrong language. This problem is more pronounced on zero-shot translation tasks. In this work, we find that failing in encoding discriminative target language signal will lead to off-target and a closer lexical distance (i.e., KL-divergence) between two languages’ vocabularies is related with a higher off-target rate. We also find that solely isolating the vocab of different languages in the decoder can alleviate the problem. Motivated by the findings, we propose Language Aware Vocabulary Sharing (LAVS), a simple and effective algorithm to construct the multilingual vocabulary, that greatly alleviates the off-target problem of the translation model by increasing the KL-divergence between languages. We conduct experiments on a multilingual machine translation benchmark in 11 languages. Experiments show that the off-target rate for 90 translation tasks is reduced from 29% to 8%, while the overall BLEU score is improved by an average of 1.9 points without extra training cost or sacrificing the supervised directions’ performance. We release the code at https://github.com/PKUnlp-icler/Off-Target-MNMT for reproduction.
Anthology ID:
2023.findings-acl.608
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9542–9558
Language:
URL:
https://aclanthology.org/2023.findings-acl.608
DOI:
10.18653/v1/2023.findings-acl.608
Bibkey:
Cite (ACL):
Liang Chen, Shuming Ma, Dongdong Zhang, Furu Wei, and Baobao Chang. 2023. On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9542–9558, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation (Chen et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-acl-2023-videos/2023.findings-acl.608.pdf