NTT-NAIST syntax-based SMT systems for IWSLT 2014

Katsuhito Sudoh, Graham Neubig, Kevin Duh, Katsuhiko Hayashi


Abstract
This paper presents NTT-NAIST SMT systems for English-German and German-English MT tasks of the IWSLT 2014 evaluation campaign. The systems are based on generalized minimum Bayes risk system combination of three SMT systems using the forest-to-string, syntactic preordering, and phrase-based translation formalisms. Individual systems employ training data selection for domain adaptation, truecasing, compound word splitting (for GermanEnglish), interpolated n-gram language models, and hypotheses rescoring using recurrent neural network language models.
Anthology ID:
2014.iwslt-evaluation.18
Volume:
Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 4-5
Year:
2014
Address:
Lake Tahoe, California
Editors:
Marcello Federico, Sebastian Stüker, François Yvon
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
127–133
Language:
URL:
https://aclanthology.org/2014.iwslt-evaluation.18
DOI:
Bibkey:
Cite (ACL):
Katsuhito Sudoh, Graham Neubig, Kevin Duh, and Katsuhiko Hayashi. 2014. NTT-NAIST syntax-based SMT systems for IWSLT 2014. In Proceedings of the 11th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 127–133, Lake Tahoe, California.
Cite (Informal):
NTT-NAIST syntax-based SMT systems for IWSLT 2014 (Sudoh et al., IWSLT 2014)
Copy Citation:
PDF:
https://aclanthology.org/2014.iwslt-evaluation.18.pdf