BriefGPT.xyz
Aug, 2017
机器翻译中利用元信息的神经和统计方法
Neural and Statistical Methods for Leveraging Meta-information in Machine Translation
HTML
PDF
Shahram Khadivi, Patrick Wilken, Leonard Dahlmann, Evgeny Matusov
TL;DR
本文研究了利用元信息及更丰富的上下文方法来改善机器翻译质量，首要关注输入文本的类别信息，采用最先进的神经网络方法在统计机器翻译框架下解决该问题，实验结果在某些文本类别上BLEU评分提高了3%。
Abstract
In this paper, we discuss different methods which use
meta information
and richer context that may accompany source language input to improve
machine translation
quality. We focus on category information of input
→