Multi-Source Neural Machine Translation with Data Augmentation

Abstract

Multi-source translation systems translate from multiple languages to a single target language. By using information from these multiple sources, these systems achieve large gains in accuracy. To train these systems, it is necessary to have corpora with parallel text in multiple sources and the target language. However, these corpora are rarely complete in practice due to the difficulty of providing human translations in all of the relevant languages. In this paper, we propose a data augmentation approach to fill such incomplete parts using multi-source neural machine translation (NMT). In our experiments, results varied over different language combinations but significant gains were observed when using a source language similar to the target language.

arXiv comment15th International Workshop on Spoken Language Translation 2018

References in corpus (1)

• Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder

Cited by in corpus (6)

• A Comprehensive Survey of Multilingual Neural Machine Translation
• Neural Polysynthetic Language Modelling
• Generalized Data Augmentation for Low-Resource Translation
• A Brief Survey of Multilingual Neural Machine Translation
• Neural Machine Translation: A Review and Survey
• Crowdsourcing Parallel Corpus for English-Oromo Neural Machine Translation using Community Engagement Platform