Massively Parallel Cross-Lingual Learning in Low-Resource Target Language Translation

Abstract

We work on translation from rich-resource languages to low-resource languages. The main challenges we identify are the lack of low-resource language data, effective methods for cross-lingual transfer, and the variable-binding problem that is common in neural systems. We build a translation system that addresses these challenges using eight European language families as our test ground. Firstly, we add the source and the target family labels and study intra-family and inter-family influences for effective cross-lingual transfer. We achieve an improvement of +9.9 in BLEU score for English-Swedish translation using eight families compared to the single-family multi-source multi-target baseline. Moreover, we find that training on two neighboring families closest to the low-resource language is often enough. Secondly, we construct an ablation study and find that reasonably good results can be achieved even with considerably less target data. Thirdly, we address the variable-binding problem by building an order-preserving named entity translation model. We obtain 60.6% accuracy in qualitative evaluation where our translations are akin to human translations in a preliminary study.

Accepted at 2018 Third Conference on Machine Translation (WMT18)

References in corpus (4)

• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder
• Incorporating Discrete Translation Lexicons into Neural Machine Translation
• Embedding Learning Through Multilingual Concept Induction