Simultaneous Neural Machine Translation with Prefix Alignment
Yasumasa Kano, Katsuhito Sudoh, Satoshi Nakamura · 2022
Simultaneous translation is a task that requires starting translation before the speaker has finished speaking, so we face a trade-off between latency and accuracy.In this work, we focus on prefix-to-prefix translation and propose a method to extract alignment between bilingual prefix pairs.We use the alignment to segment a streaming input and fine-tune a translation model.The proposed method demonstrated higher BLEU than those of baselines in low latency ranges in our experiments on the IWSLT simultaneous translation benchmark.