Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation
This work addresses real-time translation needs for users, but it is incremental as it builds on existing neural MT frameworks.
The paper tackles simultaneous translation by introducing a tunable agent for segmentation decisions and modifying training to fit incremental decoding, achieving higher BLEU scores and lower latency than prior methods.
We address the problem of simultaneous translation by modifying the Neural MT decoder to operate with dynamically built encoder and attention. We propose a tunable agent which decides the best segmentation strategy for a user-defined BLEU loss and Average Proportion (AP) constraint. Our agent outperforms previously proposed Wait-if-diff and Wait-if-worse agents (Cho and Esipova, 2016) on BLEU with a lower latency. Secondly we proposed data-driven changes to Neural MT training to better match the incremental decoding framework.