Learning to Translate in Real-time with Neural Machine Translation Learning to Translate in Real-time with Neural Machine Translation
Paper summary 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.
arxiv.org
arxiv-sanity.com
scholar.google.com
Learning to Translate in Real-time with Neural Machine Translation
Jiatao Gu and Graham Neubig and Kyunghyun Cho and Victor O. K. Li
arXiv e-Print archive - 2016 via arXiv
Keywords: cs.CL, cs.LG

more

Loading...
Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About