Improving Zero-Shot Translation of Low-Resource Languages

Abstract

Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time. We investigate here a zero-shot translation in a particularly lowresource 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.

arXiv commentPublished at the International Workshop on Spoken Language Translation (IWSLT), Tokyo, Japan, December 2017

Cited by in corpus (11)

• Multilingual NMT with a language-independent attention bridge
• A Comprehensive Survey of Multilingual Neural Machine Translation
• Low Resource Neural Machine Translation: A Benchmark for Five African Languages
• Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation
• Contextual Parameter Generation for Universal Neural Machine Translation
• Multilingual Neural Machine Translation for Zero-Resource Languages
• A Brief Survey of Multilingual Neural Machine Translation
• Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages
• Cross-lingual Word Embeddings beyond Zero-shot Machine Translation
• Self-Learning for Zero Shot Neural Machine Translation
• Learning Policies for Multilingual Training of Neural Machine Translation Systems