EBMT system of Kyoto University in OLYMPICS task at IWSLT 2012

Chenhui Chu, Toshiaki Nakazawa, Sadao Kurohashi


Abstract
This paper describes the EBMT system of Kyoto University that participated in the OLYMPICS task at IWSLT 2012. When translating very different language pairs such as Chinese-English, it is very important to handle sentences in tree structures to overcome the difference. Many recent studies incorporate tree structures in some parts of translation process, but not all the way from model training (alignment) to decoding. Our system is a fully tree-based translation system where we use the Bayesian phrase alignment model on dependency trees and example-based translation. To improve the translation quality, we conduct some special processing for the IWSLT 2012 OLYMPICS task, including sub-sentence splitting, non-parallel sentence filtering, adoption of an optimized Chinese segmenter and rule-based decoding constraints.
Anthology ID:
2012.iwslt-evaluation.12
Volume:
Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign
Month:
December 6-7
Year:
2012
Address:
Hong Kong, Table of contents
Venue:
IWSLT
SIG:
SIGSLT
Publisher:
Note:
Pages:
96–101
Language:
URL:
https://aclanthology.org/2012.iwslt-evaluation.12
DOI:
Bibkey:
Cite (ACL):
Chenhui Chu, Toshiaki Nakazawa, and Sadao Kurohashi. 2012. EBMT system of Kyoto University in OLYMPICS task at IWSLT 2012. In Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 96–101, Hong Kong, Table of contents.
Cite (Informal):
EBMT system of Kyoto University in OLYMPICS task at IWSLT 2012 (Chu et al., IWSLT 2012)
Copy Citation:
PDF:
https://aclanthology.org/2012.iwslt-evaluation.12.pdf