Improving Zero-Shot Translation of Low-Resource Languages

Surafel M. Lakew, Quintino F. Lotito, Matteo Negri, Marco Turchi, Marcello Federico


Abstract
Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zero-shot) translation directions not observed at training time. We investigate here a zero-shot translation in a particularly low-resource multilingual setting. We propose a simple iterative training procedure that leverages a duality of translations directly generated by the system for the zero-shot directions. The translations produced by the system (sub-optimal since they contain mixed language from the shared vocabulary), are then used together with the original parallel data to feed and iteratively re-train the multilingual network. Over time, this allows the system to learn from its own generated and increasingly better output. Our approach shows to be effective in improving the two zero-shot directions of our multilingual model. In particular, we observed gains of about 9 BLEU points over a baseline multilingual model and up to 2.08 BLEU over a pivoting mechanism using two bilingual models. Further analysis shows that there is also a slight improvement in the non-zero-shot language directions.
Anthology ID:
2017.iwslt-1.16
Volume:
Proceedings of the 14th International Conference on Spoken Language Translation
Month:
December 14-15
Year:
2017
Address:
Tokyo, Japan
Editors:
Sakriani Sakti, Masao Utiyama
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
International Workshop on Spoken Language Translation
Note:
Pages:
113–119
Language:
URL:
https://aclanthology.org/2017.iwslt-1.16
DOI:
Bibkey:
Cite (ACL):
Surafel M. Lakew, Quintino F. Lotito, Matteo Negri, Marco Turchi, and Marcello Federico. 2017. Improving Zero-Shot Translation of Low-Resource Languages. In Proceedings of the 14th International Conference on Spoken Language Translation, pages 113–119, Tokyo, Japan. International Workshop on Spoken Language Translation.
Cite (Informal):
Improving Zero-Shot Translation of Low-Resource Languages (Lakew et al., IWSLT 2017)
Copy Citation:
PDF:
https://aclanthology.org/2017.iwslt-1.16.pdf