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.
@article{arxiv.1806.03661,
title = {Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation},
author = {Fahim Dalvi and Nadir Durrani and Hassan Sajjad and Stephan Vogel},
journal= {arXiv preprint arXiv:1806.03661},
year = {2018}
}