Paper Info
Title
Asynchronous Bidirectional Decoding for Neural Machine Translation.
Abstract
The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-to-right manner, leaving the target-side contexts generated from right to left unexploded during translation. In this paper, we equip the conventional attentional encoder-decoder NMT framework with a backward decoder, in order to explore bidirectional decoding for NMT. Attending to the hidden state sequence produced by the encoder, our backward decoder first learns to generate the target-side hidden state sequence from right to left. Then, the forward decoder performs translation in the forward direction, while in each translation prediction timestep, it simultaneously applies two attention models to consider the source-side and reverse target-side hidden states, respectively. With this new architecture, our model is able to fully exploit source- and target-side contexts to improve translation quality altogether. Experimental results on NISI Chinese-English and WMT English-German translation tasks demonstrate that our model achieves substantial improvements over the conventional NMT by 3.14 and 1.38 BLEU points, respectively. The source code of this work can he obtained from https://github.com/DeepLearnXMLU/ABD-NMT.
Year
Venue
DocType
2018
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
Conference
Volume
Citations 
PageRank 
abs/1801.05122
8
0.43
References 
Authors
22
6
Name
Order
Citations
PageRank
Xiangwen Zhang1173.51
Jinsong Su226041.51
Yue Qin3182.08
Yang Liu41568126.97
Rongrong Ji53616189.98
Hongji Wang691.12