Detailed Information on Publication Record
2003
Context Sensitive Pattern Based Segmentation: A Thai Challenge
SOJKA, Petr and David ANTOŠBasic information
Original name
Context Sensitive Pattern Based Segmentation: A Thai Challenge
Authors
SOJKA, Petr (203 Czech Republic, guarantor) and David ANTOŠ (203 Czech Republic)
Edition
Budapest, Proceedings of EACL 2003 workshop Computational Linguistics for South Asian Languages -- Expanding Synergies with Europe, p. 65-72, 8 pp. 2003
Publisher
Association for Computational Linguistics
Other information
Language
English
Type of outcome
Stať ve sborníku
Field of Study
10201 Computer sciences, information science, bioinformatics
Country of publisher
Hungary
Confidentiality degree
není předmětem státního či obchodního tajemství
References:
RIV identification code
RIV/00216224:14330/03:00008605
Organization unit
Faculty of Informatics
ISBN
1-932432-02-7
Keywords in English
segmentation Thai competing patterns
Tags
International impact, Reviewed
Změněno: 13/2/2007 23:05, doc. RNDr. Petr Sojka, Ph.D.
Abstract
V originále
A Thai written text is a string of symbols without explicit word boundaries. A method for a development of a segmentation tool from a corpus of already segmented text is described. The methodology is based on the technology of competing patterns. A new UNICODE pattern generation program, OPATGEN, is used for the learning phase. We have shown feasibility of our methodology by generating patterns for Thai segmentation from already segmented text of the Thai corpus ORCHID: the segmentation algorithm quickly reaches F-score of 93 %. Finally, we enumerate possible new applications based on the pattern technique, and conclude with the suggestion of a general Pattern Translation Process. The technology is general and can be used for any other segmentation tasks as phonetic, morphologic segmentation, word hyphenation, sentence segmentation and text topic segmentation for any language.
Links
MSM 143300003, plan (intention) |
|