Translating in real-time, a.k.a. simultaneous translation, outputs translation words before the input sentence ends, which is a challenging problem for conventional machine translation methods. We propose a neural machine translation (NMT) framework for simultaneous translation in which an agent learns to make decisions on when to translate from the interaction with a pre-trained NMT environment. To trade off quality and delay, we extensively explore various targets for delay and design a method for beam-search applicable in the simultaneous MT setting. Experiments against state-of-the-art baselines on two language pairs demonstrate the efficacy of the proposed framework both quantitatively and qualitatively.
@article{arxiv.1610.00388,
title = {Learning to Translate in Real-time with Neural Machine Translation},
author = {Jiatao Gu and Graham Neubig and Kyunghyun Cho and Victor O. K. Li},
journal= {arXiv preprint arXiv:1610.00388},
year = {2017}
}