Studying The Impact Of Document-level Context On Simultaneous Neural Machine Translation
Machine Translation Summit
In a real-time simultaneous translation setting, neural machine translation (NMT) models start generating target language tokens from incomplete source language sentences, making them harder to translate, leading to poor translation quality. Previous research has shown that document-level NMT, comprising of sentence and context encoders and a decoder, leverages context from neighbouring sentences and helps improve translation quality. In simultaneous translation settings, the context from
... us sentences should be even more critical. To this end, in this paper, we propose wait-k simultaneous document-level NMT where we keep the context encoder as it is and replace the source sentence encoder and target language decoder with their wait-k equivalents. We experiment with low and high resource settings using the Asian Language Treebank (ALT) and OpenSubtitles2018 corpora, where we observe minor improvements in translation quality. We then perform an analysis of the translations obtained using our models by focusing on sentences that should benefit from the context where we found out that the model does, in fact, benefit from context but is unable to effectively leverage it, especially in a low-resource setting. This shows that there is a need for further innovation in the way useful context is identified and leveraged.