BriefGPT.xyz
Jun, 2016
将离散的翻译词典融入神经机器翻译
Incorporating Discrete Translation Lexicons into Neural Machine Translation
HTML
PDF
Philip Arthur, Graham Neubig, Satoshi Nakamura
TL;DR
本文提出使用离散的翻译词典，通过使用NMT模型的attention向量选择需要聚焦的源单词的词典概率，从而缓解NMT在翻译低频词汇时出现的错误，并进行了两种方法的实验，结果显示翻译质量（BLEU）得分有明显提高。
Abstract
neural machine translation
(NMT) often makes mistakes in translating
low-frequency content words
that are essential to understanding the meaning of the sentence. We propose a method to alleviate this problem by a
→