{"type":"ScholarlyArticle","title":"Agreement-Based Joint Training for Bidirectional Attention-Based Neural Machine Translation","authors":[{"name":"Yong Cheng","slug":"yong-cheng","given":"Yong","family":"Cheng","affiliation":""},{"name":"Shiqi Shen","slug":"shiqi-shen","given":"Shiqi","family":"Shen","affiliation":""},{"name":"Zhongjun He","slug":"zhongjun-he","given":"Zhongjun","family":"He","affiliation":""},{"name":"Wei He","slug":"wei-he","given":"Wei","family":"He","affiliation":""},{"name":"Hua Wu","slug":"hua-wu","given":"Hua","family":"Wu","affiliation":""},{"name":"Maosong Sun","slug":"maosong-sun","given":"Maosong","family":"Sun","affiliation":""},{"name":"Yang Liu","slug":"yang-liu-3","given":"Yang","family":"Liu","affiliation":""}],"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.","doi":null,"url":"https://ijcai.org/proceedings/2016/392","pdf":"https://ijcai.org/proceedings/2016/0392.pdf","markdown":"https://ijcai.org/proceedings/2016/392.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/392","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":392,"pages":{"first":2761,"last":2766},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}