English

Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement

Computation and Language 2021-10-20 v1 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2110.09646,
  title  = {Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement},
  author = {HyoJung Han and Seokchan Ahn and Yoonjung Choi and Insoo Chung and Sangha Kim and Kyunghyun Cho},
  journal= {arXiv preprint arXiv:2110.09646},
  year   = {2021}
}

Comments

To be published in WMT2021

R2 v1 2026-06-24T06:59:33.314Z