Mahidol University Logo
Faculty of ICT, Mahidol University
 

Admissions

Printable Version

 

BILINGUAL MACHINE READABLE DICTIONARY EXTRACTION AND CONCEPT TREE CONSTRUCTTION FOR THAI WORDNET DEVELOPMENT

 

TITLE BILINGUAL MACHINE READABLE DICTIONARY EXTRACTION AND CONCEPT TREE CONSTRUCTTION FOR THAI WORDNET DEVELOPMENT
AUTHOR YUTTHANA PIRUNSARN
DEGREE MASTER OF SCIENCE PROGRAMME IN COMPUTER SCIENCE
FACULTY FACULTY OF SCIENCE
ADVISOR CHARNYOTE PLUEMPITIWIRIYAWEJ
CO-ADVISOR SRISUPA PALAKVANGSA NA AYUDHYA
 
ABSTRACT
This thesis describes an approach that supports the automatic construction and development of Thai WordNet. The approach consists of two parts: the bilingual machine readable dictionaries extraction and the concept tree construction. In the extraction process, different MRDs representing different file formats were taken into account. These MRDs were reformatted, cleaned, integrated and selected to obtain a set of Thai nominal words. In the construction process, these Thai words were analyzed with regards to a primary hypothesis which states that words with the same prefix are likely to be related to others in hierarchical arrangement. The relationships between Thai words were constructed and represented in the form of the concept tree. We also developed a software tool to help evaluate the correctness of the concept tree. The tool allows two groups of users to evaluate the same set of trees. The result of evaluation was analyzed by using the Kappa statistic. The Kappa analysis showed that our approach was promising.
KEYWORD BILINGUAL MACHINE READABLE DICTIONARY / CONCEPT TREE / THAI WORDNET

 

 

Go to Top

 

ICT Building, Mahidol University, 999 Phuttamonthon 4 Road, Salaya, Nakhonpathom 73170 Tel. +66 02 441-0909 Fax. +66 02 849-6099
Mahidol University Computing Center, The Faculty of ICT, Mahidol University , Rama 6 Road, Rajathevi, Bangkok 10400 Tel. +66 02 354-4333 Fax. +66 02 354-7333