TY - GEN
T1 - Sentence-level agreement for neural machine translation
AU - Yang, Mingming
AU - Wang, Rui
AU - Chen, Kehai
AU - Utiyama, Masao
AU - Sumita, Eiichiro
AU - Zhang, Min
AU - Zhao, Tiejun
N1 - Publisher Copyright:
© 2019 Association for Computational Linguistics.
PY - 2020
Y1 - 2020
N2 - The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references. In NMT, there is a natural correspondence between the source sentence and the target sentence. However, this relationship has only been represented using the entire neural network and the training objective is computed in word-level. In this paper, we propose a sentence-level agreement module to directly minimize the difference between the representation of source and target sentence. The proposed agreement module can be integrated into NMT as an additional training objective function and can also be used to enhance the representation of the source sentences. Empirical results on the NIST Chinese-to-English and WMT English-to-German tasks show the proposed agreement module can significantly improve the NMT performance.
AB - The training objective of neural machine translation (NMT) is to minimize the loss between the words in the translated sentences and those in the references. In NMT, there is a natural correspondence between the source sentence and the target sentence. However, this relationship has only been represented using the entire neural network and the training objective is computed in word-level. In this paper, we propose a sentence-level agreement module to directly minimize the difference between the representation of source and target sentence. The proposed agreement module can be integrated into NMT as an additional training objective function and can also be used to enhance the representation of the source sentences. Empirical results on the NIST Chinese-to-English and WMT English-to-German tasks show the proposed agreement module can significantly improve the NMT performance.
UR - https://www.scopus.com/pages/publications/85084050989
M3 - 会议稿件
AN - SCOPUS:85084050989
T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
SP - 3076
EP - 3082
BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Y2 - 28 July 2019 through 2 August 2019
ER -