Neural Machine Translation via Binary Code Prediction
arXiv:1704.06918
Abstract
In this paper, we propose a new method for calculating the output layer in neural machine translation systems. The method is based on predicting a binary code for each word and can reduce computation time/memory requirements of the output layer to be logarithmic in vocabulary size in the best case. In addition, we also introduce two advanced approaches to improve the robustness of the proposed model: using error-correcting codes and combining softmax and binary codes. Experiments on two English-Japanese bidirectional translation tasks show proposed models achieve BLEU scores that approach the softmax, while reducing memory usage to the order of less than 1/10 and improving decoding speed on CPUs by x5 to x10.
arXiv commentAccepted as a long paper at ACL2017
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Effective Approaches to Attention-based Neural Machine Translation
- DyNet: The Dynamic Neural Network Toolkit
- Character-based Neural Machine Translation
- Vocabulary Selection Strategies for Neural Machine Translation