Integration Algorithm of English-Chinese Word Segmentation and Alignment

Author

Xu, Zhi-Ming ; Kit, Chun-yu ; Webster, Jonathan J.

Author_Institution

Dept. of Comput. Sci. & Technol., Harbin Inst. of Technol.

fYear

2006

fDate

13-16 Aug. 2006

Firstpage

4105

Lastpage

4110

Abstract

This paper proposes an integration algorithm of English-Chinese word segmentation and alignment. In this algorithm, bilingual word segmentation and alignment work synchronously and interactively. Given sentence-aligned bitext, it cannot only use bilingual word alignment´s information to guide resolving word segmentation ambiguities, but also avoid the errors of word segmentation from being transferred into word alignment. Experimental result shows that it distinctly improves accuracy of both word segmentation and alignment

Keywords

dictionaries; language translation; natural languages; word processing; English-Chinese word segmentation; bilingual dictionary; bilingual word alignment; bilingual word segmentation; example-based machine translation; integration algorithm; sentence-aligned bitext; Computer science; Cybernetics; Data mining; Dictionaries; Iterative algorithms; Iterative methods; Learning systems; Machine learning; Machine learning algorithms; Word segmentation; example-based machine translation; word alignment; word similarity;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2006 International Conference on

Conference_Location

Dalian, China

Print_ISBN

1-4244-0061-9

Type

conf

DOI

10.1109/ICMLC.2006.258869

Filename

4028790