Forest-Based Neural Machine Translation

Chunpeng Ma, Akihiro Tamura, Masao Utiyama, Tiejun Zhao, Eiichiro Sumita


Abstract
Tree-based neural machine translation (NMT) approaches, although achieved impressive performance, suffer from a major drawback: they only use the 1-best parse tree to direct the translation, which potentially introduces translation mistakes due to parsing errors. For statistical machine translation (SMT), forest-based methods have been proven to be effective for solving this problem, while for NMT this kind of approach has not been attempted. This paper proposes a forest-based NMT method that translates a linearized packed forest under a simple sequence-to-sequence framework (i.e., a forest-to-sequence NMT model). The BLEU score of the proposed method is higher than that of the sequence-to-sequence NMT, tree-based NMT, and forest-based SMT systems.
Anthology ID:
P18-1116
Original:
P18-1116v1
Version 2:
P18-1116v2
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1253–1263
Language:
URL:
https://aclanthology.org/P18-1116
DOI:
10.18653/v1/P18-1116
Bibkey:
Cite (ACL):
Chunpeng Ma, Akihiro Tamura, Masao Utiyama, Tiejun Zhao, and Eiichiro Sumita. 2018. Forest-Based Neural Machine Translation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1253–1263, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Forest-Based Neural Machine Translation (Ma et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1116.pdf
Presentation:
 P18-1116.Presentation.pdf
Video:
 https://vimeo.com/285803442