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.

READ FULL TEXT

Authors

page 14

page 15

Code Repositories

lowrank-gru

Gated Recurrent Unit with Low-rank matrix factorization


view repo

sequence-translation

RNN encoder/decoder model for sequence translation


view repo

SequenceToSequenceLearning

Sequence to Sequence学习简述


view repo

Fake-News-Challenge

Machine Learning in fighting fake news


view repo

keyword_spotting

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.