Efficient Bidirectional Neural Machine Translation
arXiv:1908.09329
Abstract
The encoder-decoder based neural machine translation usually generates a target sequence token by token from left to right. Due to error propagation, the tokens in the right side of the generated sequence are usually of poorer quality than those in the left side. In this paper, we propose an efficient method to generate a sequence in both left-to-right and right-to-left manners using a single encoder and decoder, combining the advantages of both generation directions. Experiments on three translation tasks show that our method achieves significant improvements over conventional unidirectional approach. Compared with ensemble methods that train and combine two models with different generation directions, our method saves 50% model parameters and about 40% training time, and also improve inference speed.
References in corpus (12)
- Adam: A Method for Stochastic Optimization
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- Convolutional Sequence to Sequence Learning
- Temporal Ensembling for Semi-Supervised Learning
- MASS: Masked Sequence to Sequence Pre-training for Language Generation
- Achieving Human Parity on Automatic Chinese to English News Translation
- Neural Machine Translation in Linear Time
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- Almost Unsupervised Text to Speech and Automatic Speech Recognition
- Towards Robust Neural Networks via Random Self-ensemble
- Towards Neural Phrase-based Machine Translation
- Dense Information Flow for Neural Machine Translation