Key points are not available for this paper at this time.
本文提出了一种新颖的神经网络模型,称为RNN编码器-解码器,该模型由两个循环神经网络(RNN)组成。一个RNN将符号序列编码为固定长度的向量表示,另一个RNN将该表示解码为另一符号序列。所提出模型的编码器和解码器联合训练,以最大化给定源序列下目标序列的条件概率。实验证明,在现有对数线性模型中使用RNN编码器-解码器计算的短语对条件概率作为额外特征,可以提升统计机器翻译系统的性能。定性分析显示,该模型学习到了具有语义和句法意义的语言短语表示。
Building similarity graph...
Analyzing shared references across papers
Loading...
Kyunghyun Cho
Bart van Merriënboer
Çaǧlar Gülçehre
Université de Montréal
Canadian Institute for Advanced Research
Constructor University
Building similarity graph...
Analyzing shared references across papers
Loading...
Cho等人(Tue,)研究了这个问题。
www.synapsesocial.com/papers/696402a893519ba8671d0489 — DOI: https://doi.org/10.48550/arxiv.1406.1078
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: