a single sentence does not always convey information required to translate it into other languages: we sometimes need to add or specialize words that are omitted or ambiguous in the source languages (e.g.. zero pronouns in translating Japanese to English or epicene pronouns in translating English to French). To translate such ambiguous sentences, we exploit contexts around the source sentence, and have so far explored context-aware neural machine translation (NMT). However, a large amount of parallel corpora is not easily available to train accurate context-aware NMT models. In this study, we first obtain large-scale pseudo parallel corpora by back-translating target-side monolingual corpora, and then investigate its impact on the translation performance of context-aware NMT models. We evaluate NMT models trained with small parallel corpora and the large-scale pseudo parallel corpora on IWSLT2017 English-Japanese and English-French datasets, and demonstrate the large impact of the data augmentation for context-aware NMT models in terms of bleu score and specialized test sets on ja→en~1 and fr→en.
展开▼
