NTT statistical machine translation system for IWSLT 2008.

Katsuhito Sudoh, Taro Watanabe, Jun Suzuki, Hajime Tsukada, Hideki Isozaki


Abstract
The NTT Statistical Machine Translation System consists of two primary components: a statistical machine translation decoder and a reranker. The decoder generates k-best translation canditates using a hierarchical phrase-based translation based on synchronous context-free grammar. The decoder employs a linear feature combination among several real-valued scores on translation and language models. The reranker reorders the k-best translation candidates using Ranking SVMs with a large number of sparse features. This paper describes the two components and presents the results for the evaluation campaign of IWSLT 2008.
Anthology ID:
2008.iwslt-evaluation.13
Volume:
Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
October 20-21
Year:
2008
Address:
Waikiki, Hawaii
Venue:
IWSLT
SIG:
Publisher:
Note:
Pages:
92–97
Language:
URL:
https://aclanthology.org/2008.iwslt-evaluation.13
DOI:
Bibkey:
Cite (ACL):
Katsuhito Sudoh, Taro Watanabe, Jun Suzuki, Hajime Tsukada, and Hideki Isozaki. 2008. NTT statistical machine translation system for IWSLT 2008.. In Proceedings of the 5th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 92–97, Waikiki, Hawaii.
Cite (Informal):
NTT statistical machine translation system for IWSLT 2008. (Sudoh et al., IWSLT 2008)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2008.iwslt-evaluation.13.pdf