---
title: "Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation"
authors:
  - "Yong Cheng"
  - "Shiqi Shen"
  - "Zhongjun He"
  - "Wei He"
  - "Hua Wu"
  - "Maosong Sun"
  - "Yang Liu"
doi: ""
url: "https://ijcai.org/proceedings/2016/392"
pdf: "https://ijcai.org/proceedings/2016/0392.pdf"
venue: "Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence"
year: 2016
pages: "2761-2766"
track: ""
keywords:
---

# 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

*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.