TY - GEN
T1 - Neural machine translation with source dependency representation
AU - Chen, Kehai
AU - Wang, Rui
AU - Utiyama, Masao
AU - Liu, Lemao
AU - Tamura, Akihiro
AU - Sumita, Eiichiro
AU - Zhao, Tiejun
N1 - Publisher Copyright:
© 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - Source dependency information has been successfully introduced into statistical machine translation. However, there are only a few preliminary attempts for Neural Machine Translation (NMT), such as concatenating representations of source word and its dependency label together. In this paper, we propose a novel attentional NMT with source dependency representation to improve translation performance of NMT, especially on long sentences. Empirical results on NIST Chinese-to-English translation task show that our method achieves 1.6 BLEU improvements on average over a strong NMT system.
AB - Source dependency information has been successfully introduced into statistical machine translation. However, there are only a few preliminary attempts for Neural Machine Translation (NMT), such as concatenating representations of source word and its dependency label together. In this paper, we propose a novel attentional NMT with source dependency representation to improve translation performance of NMT, especially on long sentences. Empirical results on NIST Chinese-to-English translation task show that our method achieves 1.6 BLEU improvements on average over a strong NMT system.
UR - https://www.scopus.com/pages/publications/85051583047
U2 - 10.18653/v1/d17-1304
DO - 10.18653/v1/d17-1304
M3 - 会议稿件
AN - SCOPUS:85051583047
T3 - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
SP - 2846
EP - 2852
BT - EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PB - Association for Computational Linguistics (ACL)
T2 - 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017
Y2 - 9 September 2017 through 11 September 2017
ER -