June 20 , 2014, 2PM 302- 309-1
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. (paper: http://arxiv.org/abs/1406.1078) |