Deconvolution-Based Global Decoding for Neural Machine Translation
arXiv:1806.03692
Abstract
A great proportion of sequence-to-sequence (Seq2Seq) models for Neural Machine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. As the studies of linguistics have proved that language is not linear word sequence but sequence of complex structure, translation at each step should be conditioned on the whole target-side context. To tackle the problem, we propose a new NMT model that decodes the sequence with the guidance of its structural prediction of the context of the target sequence. Our model generates translation based on the structural prediction of the target-side context so that the translation can be freed from the bind of sequential order. Experimental results demonstrate that our model is more competitive compared with the state-of-the-art methods, and the analysis reflects that our model is also robust to translating sentences of different lengths and it also reduces repetition with the instruction from the target-side context for decoding.
arXiv commentAccepted by COLING 2018
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- Convolutional Sequence to Sequence Learning
- Effective Approaches to Attention-based Neural Machine Translation
- Learning Deconvolution Network for Semantic Segmentation
- A Convolutional Neural Network for Modelling Sentences
- Lattice-Based Recurrent Neural Network Encoders for Neural Machine Translation
- Coverage Embedding Models for Neural Machine Translation
- Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks
- Memory-enhanced Decoder for Neural Machine Translation
- Global Encoding for Abstractive Summarization
- Decoding-History-Based Adaptive Control of Attention for Neural Machine Translation