Prefix Alignment for Training Simultaneous Machine Translation

Abstract

Simultaneous translation is a task that starts translation even before the speaker has finished speaking. This study focuses on prefix-to-prefix translation and proposes a method to align prefixes in a bilingual sentence pair iteratively to train a machine translation model to work with prefix-to-prefix. In the experiments, the proposed method demonstrated higher BLEU than those of the baseline methods in low latency ranges on the IWSLT simultaneous translation benchmark. However, the proposed method degraded the performance in high latency ranges in the English-to-Japanese experiments; thus, we analyzed it in length ratios and prefix boundary prediction accuracies. The obtained results suggested that the degraded performance was due to the large word order difference between English and Japanese.