BriefGPT.xyz
Oct, 2015
神经重排序提高机器翻译的主观质量: NAIST在WAT2015上的表现
Neural Reranking Improves Subjective Quality of Machine Translation: NAIST at WAT2015
HTML
PDF
Graham Neubig, Makoto Morishita, Satoshi Nakamura
TL;DR
研究表明，使用基于语法的统计机器翻译加上使用神经注意力机器翻译模型的重新排序组件进行机器翻译的效果较好，尤其对于语法正确性方面有较大提升。
Abstract
This year, the Nara Institute of Science and Technology (NAIST)'s submission to the 2015 Workshop on Asian Translation was based on
syntax-based statistical machine translation
, with the addition of a
reranking
c
→