Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement
This addresses latency issues in simultaneous translation for specific language pairs, but it is incremental as it builds on existing wait-k models with data preprocessing.
The paper tackles the problem of high latency in simultaneous machine translation for languages with differing word orders by proposing an algorithm to reorder and refine target sentences to align monotonically with source sentences, which improves BLEU scores and enhances translation monotonicity.
Recent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the expense of the grammaticality of a sentence being translated. In this paper, we thus propose an algorithm to reorder and refine the target side of a full sentence translation corpus, so that the words/phrases between the source and target sentences are aligned largely monotonically, using word alignment and non-autoregressive neural machine translation. We then train a widely used wait-k simultaneous translation model on this reordered-and-refined corpus. The proposed approach improves BLEU scores and resulting translations exhibit enhanced monotonicity with source sentences.