Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation

Cheng, Yong; Shen, Shiqi; He, Zhongjun; He, Wei; Wu, Hua; Sun, Maosong; Liu, Yang

Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation

Yong Cheng, Shiqi Shen, Zhongjun He, Wei He, Hua Wu, Maosong Sun, Yang Liu

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2761-2766.

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.

Yong Cheng, Shiqi Shen, Zhongjun He, Wei He, Hua Wu, Maosong Sun, and Yang Liu. 2016. Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 2761–2766. https://ijcai.org/proceedings/2016/392

@inproceedings{ijcai2016p392,
  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 = {Proceedings of the Twenty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-16}},
  publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
  editor    = {Subbarao Kambhampati},
  pages     = {2761--2766},
  year      = {2016},
  month     = {7},
  url       = {https://ijcai.org/proceedings/2016/392},
}

TY  - CPAPER
TI  - Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation
AU  - Cheng, Yong
AU  - Shen, Shiqi
AU  - He, Zhongjun
AU  - He, Wei
AU  - Wu, Hua
AU  - Sun, Maosong
AU  - Liu, Yang
T2  - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16
PB  - AAAI Press / International Joint Conferences on Artificial Intelligence
PY  - 2016
SP  - 2761
EP  - 2766
UR  - https://ijcai.org/proceedings/2016/392
ER  -