Asynchronous Bidirectional Decoding for Neural Machine Translation
arXiv:1801.05122
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-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.
arXiv commentaccepted by AAAI 18
References in corpus (7)
- Sequence to Sequence Learning with Neural Networks
- Modeling Coverage for Neural Machine Translation
- Twin Networks: Matching the Future for Sequence Generation
- Neural System Combination for Machine Translation
- An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing
- Deep Neural Machine Translation with Linear Associative Unit
- Towards Decoding as Continuous Optimization in Neural Machine Translation
Cited by in corpus (5)
- Towards Robust Neural Machine Translation
- Improving Bidirectional Decoding with Dynamic Target Semantics in Neural Machine Translation
- Synchronous Bidirectional Neural Machine Translation
- iCap: Interactive Image Captioning with Predictive Text
- Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks