论文信息 - EBMT System of KYOTO Team in PatentMT Task at NTCIR-9

EBMT System of KYOTO Team in PatentMT Task at NTCIR-9

This paper describes “KYOTO” EBMT system that attended PatentMT task at NTCIR-9. When translating very different language pairs such as Japanese-English and ChineseEnglish, it is very important to handle sentences in tree structures to overcome the difference. Some works incorporate tree structures in some parts of whole translation process, but not all the way from model training (parallel sentence alignment) to decoding. “KYOTO” system is a fully tree-based translation system where we use the Bayesian phrase alignment model on dependency trees and examplebased translation.

Sadao Kurohashi | Toshiaki Nakazawa

[1] Masao Utiyama,et al. Reordering Constraint Based on Document-Level Context , 2011, ACL.

[2] Sadao Kurohashi,et al. Bayesian Subtree Alignment Model based on Dependency Trees , 2011, IJCNLP.

[3] Eiichiro Sumita,et al. Overview of the Patent Machine Translation Task at the NTCIR-10 Workshop , 2011, NTCIR.

[4] Hitoshi Isahara,et al. Dependency Parsing with Short Dependency Relations in Unlabeled Data , 2008, IJCNLP.

[5] Sadao Kurohashi,et al. Fully Syntactic EBMT System of KYOTO Team in NTCIR-8 , 2010, NTCIR.

[6] Sadao Kurohashi,et al. Efficient retrieval of tree translation examples for Syntax-Based Machine Translation , 2011, EMNLP.

[7] Dan Klein,et al. Joint Parsing and Alignment with Weakly Synchronized Grammars , 2010, NAACL.