The attentional mechanism has proven to be effective in improving end-to-end neural machine translation. However, due to the intricate structural divergence between natural languages, unidirectional attention-based models might only capture partial aspects of attentional regularities. We propose agreement-based joint training for bidirectional attention-based end-to-end neural machine translation. Instead of training source-to-target and target-to-source translation models independently,our approach encourages the two complementary models to agree on word alignment matrices on the same training data. Experiments on Chinese-English and English-French translation tasks show that agreement-based joint training significantly improves both alignment and translation quality over independent training.
@article{arxiv.1512.04650,
title = {Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation},
author = {Yong Cheng and Shiqi Shen and Zhongjun He and Wei He and Hua Wu and Maosong Sun and Yang Liu},
journal= {arXiv preprint arXiv:1512.04650},
year = {2016}
}