Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation
Abstract
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. PDF
Cite
Text
Cheng et al. "Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation." International Joint Conference on Artificial Intelligence, 2016.Markdown
[Cheng et al. "Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation." International Joint Conference on Artificial Intelligence, 2016.](https://mlanthology.org/ijcai/2016/cheng2016ijcai-agreement/)BibTeX
@inproceedings{cheng2016ijcai-agreement,
title = {{Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation}},
author = {Cheng, Yong and Shen, Shiqi and He, Zhongjun and He, Wei and Wu, Hua and Sun, Maosong and Liu, Yang},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2016},
pages = {2761-2767},
url = {https://mlanthology.org/ijcai/2016/cheng2016ijcai-agreement/}
}