Learning to Translate in Real-time with Neural Machine Translation
Victor O. K. Li
arXiv e-Print archive - 2016 via Local arXiv
First published: 2016/10/03 (4 years ago) Abstract: 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.
The authors propose a framework where a Reinforcement Learning agents makes decisions of reading the next input words or producing the next output word to trade off translation quality and time delay (caused by read operations). The reward function is based on both quality (BLEU score) and delay (various metrics and hyperparameters). The authors use Policy Gradient to optimize the model, which is initialized from a pre-trained translation model. They apply to approach to WMT'15 EN-DE and EN-RU translation and show that the model increases translation quality in all settings and is able to trade off effectively between quality and delay.