learning Phrase Representations: Difference between revisions

From statwiki
Jump to navigation Jump to search
(Created page with "= Introduction = In this paper, Cho et al. propose a novel neural network model called RNN Encoder–Decoder that consists of two recurrent neural networks (RNN). One RNN encode...")
 
No edit summary
Line 4: Line 4:


= RNN Encoder–Decoder =
= RNN Encoder–Decoder =
<center>
[[File:encdec1.png | frame | center |Fig 1. Comparison of linear convolution layer and mlpconv layer ]]
</center>

Revision as of 20:45, 16 November 2015

Introduction

In this paper, Cho et al. 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.

RNN Encoder–Decoder

File:encdec1.png
Fig 1. Comparison of linear convolution layer and mlpconv layer