Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

06/03/2014 ∙ by Kyunghyun Cho, et al. ∙ 0

In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes the representation into another sequence of symbols. The encoder and decoder of the proposed model are jointly trained to maximize the conditional probability of a target sequence given a source sequence. The performance of a statistical machine translation system is empirically found to improve by using the conditional probabilities of phrase pairs computed by the RNN Encoder-Decoder as an additional feature in the existing log-linear model. Qualitatively, we show that the proposed model learns a semantically and syntactically meaningful representation of linguistic phrases.



page 14

page 15

Code Repositories


Gated Recurrent Unit with Low-rank matrix factorization

view repo


RNN encoder/decoder model for sequence translation

view repo


Sequence to Sequence学习简述

view repo


Machine Learning in fighting fake news

view repo


Chinese keyword spotting model using LSTM RNN

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.