Neural Machine Translation with Extended Context
This is an incremental study on enhancing translation coherence for machine translation systems.
The paper tackled the problem of improving neural machine translation by using extended context beyond single sentences, and found that models learned to distinguish between segments and showed robustness in translation quality, with some cases showing improved textual coherence.
We investigate the use of extended context in attention-based neural machine translation. We base our experiments on translated movie subtitles and discuss the effect of increasing the segments beyond single translation units. We study the use of extended source language context as well as bilingual context extensions. The models learn to distinguish between information from different segments and are surprisingly robust with respect to translation quality. In this pilot study, we observe interesting cross-sentential attention patterns that improve textual coherence in translation at least in some selected cases.