Universal Neural Machine Translation for Extremely Low Resource Languages
Abstract
In this paper, we propose a new universal machine translation approach focusing on languages with a limited amount of parallel data. Our proposed approach utilizes a transfer-learning approach to share lexical and sentence level representations across multiple source languages into one target language. The lexical part is shared through a Universal Lexical Representation to support multilingual word-level sharing. The sentence-level sharing is represented by a model of experts from all source languages that share the source encoders with all other languages. This enables the low-resource language to utilize the lexical and sentence representations of the higher resource languages. Our approach is able to achieve 23 BLEU on Romanian-English WMT2016 using a tiny parallel corpus of 6k sentences, compared to the 18 BLEU of strong baseline system which uses multilingual training and back-translation. Furthermore, we show that the proposed approach can achieve almost 20 BLEU on the same dataset through fine-tuning a pre-trained multi-lingual system in a zero-shot setting.
Cite
@article{arxiv.1802.05368,
title = {Universal Neural Machine Translation for Extremely Low Resource Languages},
author = {Jiatao Gu and Hany Hassan and Jacob Devlin and Victor O. K. Li},
journal= {arXiv preprint arXiv:1802.05368},
year = {2018}
}
Comments
NAACL-HLT 2018