BriefGPT.xyz
Sep, 2014
利用自动分割克服神经机器翻译中句子长度的诅咒
Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation
HTML
PDF
Jean Pouget-Abadie, Dzmitry Bahdanau, Bart van Merrienboer, Kyunghyun Cho, Yoshua Bengio
TL;DR
该研究通过将输入句子自动分割成易于神经机器翻译模型翻译的短语来解决长句翻译时翻译质量下降的问题，并证明了这种方法在长句翻译质量上有显著提升。
Abstract
The authors of (Cho et al., 2014a) have shown that the recently introduced neural network translation systems suffer from a significant drop in
translation quality
when translating
long sentences
, unlike existing
→