BriefGPT.xyz
Dec, 2016
通过最小化与句法翻译格子相关的贝叶斯风险进行神经机器翻译
Neural Machine Translation by Minimising the Bayes-risk with Respect to Syntactic Translation Lattices
HTML
PDF
Felix Stahlberg, Adrià de Gispert, Eva Hasler, Bill Byrne
TL;DR
该研究提出了一种将神经机器翻译（NMT）与传统的统计机器翻译（SMT）相结合的新方案，利用贝叶斯风险进行组合，并成功地在英德和日英翻译方面得到了显著的提升。
Abstract
We present a novel scheme to combine
neural machine translation
(NMT) with traditional
statistical machine translation
(SMT). Our approach borrows ideas from linearised lattice minimum
→