TY - GEN
T1 - Unsupervised bilingual word embedding agreement for unsupervised neural machine translation
AU - Sun, Haipeng
AU - Wang, Rui
AU - Chen, Kehai
AU - Utiyama, Masao
AU - Sumita, Eiichiro
AU - Zhao, Tiejun
N1 - Publisher Copyright:
© 2019 Association for Computational Linguistics
PY - 2020
Y1 - 2020
N2 - Unsupervised bilingual word embedding (UBWE), together with other technologies such as back-translation and denoising, has helped unsupervised neural machine translation (UNMT) achieve remarkable results in several language pairs. In previous methods, UBWE is first trained using nonparallel monolingual corpora and then this pre-trained UBWE is used to initialize the word embedding in the encoder and decoder of UNMT. That is, the training of UBWE and UNMT are separate. In this paper, we first empirically investigate the relationship between UBWE and UNMT. The empirical findings show that the performance of UNMT is significantly affected by the performance of UBWE. Thus, we propose two methods that train UNMT with UBWE agreement. Empirical results on several language pairs show that the proposed methods significantly outperform conventional UNMT.
AB - Unsupervised bilingual word embedding (UBWE), together with other technologies such as back-translation and denoising, has helped unsupervised neural machine translation (UNMT) achieve remarkable results in several language pairs. In previous methods, UBWE is first trained using nonparallel monolingual corpora and then this pre-trained UBWE is used to initialize the word embedding in the encoder and decoder of UNMT. That is, the training of UBWE and UNMT are separate. In this paper, we first empirically investigate the relationship between UBWE and UNMT. The empirical findings show that the performance of UNMT is significantly affected by the performance of UBWE. Thus, we propose two methods that train UNMT with UBWE agreement. Empirical results on several language pairs show that the proposed methods significantly outperform conventional UNMT.
UR - https://www.scopus.com/pages/publications/85084068751
M3 - 会议稿件
AN - SCOPUS:85084068751
T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
SP - 1235
EP - 1245
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 -