Improving Neural Machine Translation through Phrase-based Forced Decoding

Jingyi Zhang, Masao Utiyama, Eiichro Sumita, Graham Neubig, Satoshi Nakamura

Abstract
Compared to traditional statistical machine translation (SMT), neural machine translation (NMT) often sacrifices adequacy for the sake of fluency. We propose a method to combine the advantages of traditional SMT and NMT by exploiting an existing phrase-based SMT model to compute the phrase-based decoding cost for an NMT output and then using the phrase-based decoding cost to rerank the n-best NMT outputs. The main challenge in implementing this approach is that NMT outputs may not be in the search space of the standard phrase-based decoding algorithm, because the search space of phrase-based SMT is limited by the phrase-based translation rule table. We propose a soft forced decoding algorithm, which can always successfully find a decoding path for any NMT output. We show that using the forced decoding cost to rerank the NMT outputs can successfully improve translation quality on four different language pairs.
Anthology ID:
I17-1016
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
152–162
Language:
URL:
https://aclanthology.org/I17-1016
DOI:
Bibkey:
Cite (ACL):
Jingyi Zhang, Masao Utiyama, Eiichro Sumita, Graham Neubig, and Satoshi Nakamura. 2017. Improving Neural Machine Translation through Phrase-based Forced Decoding. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 152–162, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Improving Neural Machine Translation through Phrase-based Forced Decoding (Zhang et al., IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/I17-1016.pdf
PDF Search