Asynchronous Bidirectional Decoding for Neural Machine Translation

01/16/2018
by   Xiangwen Zhang, et al.
0

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-toright manner, leaving the target-side contexts generated from right to left unexploited 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 NIST 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 be obtained from https://github.com/DeepLearnXMU/ABDNMT.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/13/2019

Synchronous Bidirectional Neural Machine Translation

Existing approaches to neural machine translation (NMT) generate the tar...
research
08/05/2017

Neural Machine Translation with Word Predictions

In the encoder-decoder architecture for neural machine translation (NMT)...
research
12/16/2021

Learning and Analyzing Generation Order for Undirected Sequence Models

Undirected neural sequence models have achieved performance competitive ...
research
09/03/2019

Multi-agent Learning for Neural Machine Translation

Conventional Neural Machine Translation (NMT) models benefit from the tr...
research
02/28/2022

Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation

Most dominant neural machine translation (NMT) models are restricted to ...
research
11/01/2018

Language-Independent Representor for Neural Machine Translation

Current Neural Machine Translation (NMT) employs a language-specific enc...
research
01/11/2017

Towards Decoding as Continuous Optimization in Neural Machine Translation

We propose a novel decoding approach for neural machine translation (NMT...

Please sign up or login with your details

Forgot password? Click here to reset