Mahidol University Logo
Faculty of ICT, Mahidol University
 

Admissions

Printable Version

 

PARSING THAI TEXT WITH SYNTAX AND FEATURES OF WORDS

 

TITLE PARSING THAI TEXT WITH SYNTAX AND FEATURES OF WORDS.
AUTHOR CHANIN MAHATTANACHAI
DEGREE MASTER OF SCIENCE PROGRAMME IN COMPUTER SCIENCE
FACULTY FACULTY OF SCIENCE
ADVISOR DAMRAS WONGSAWANG
CO-ADVISOR SUKANYA PHONGSUPHAP
 
ABSTRACT
Parsing Thai words is to find the boundary of each word in a Thai sentence. This thesis studies the shortcomings that are incurred by word parsing. It has been found that specific names, technical terms and names of places play a significant role in the accuracy of word parsing. Those words don’t appear in a dictionary of Thai words while there is a high chance to find then in Thai documents, especially those derived from the Internet. This thesis proposed an approach for word segmentations called “Parsing Thai Text with Syntax and Features of Words” or PTTSF. This thesis discusses the PTTSF approach in detail, including analytical criteria and an implementation of the approach. The PTTSF prototype is developed and tested. The approach used the longest-matching method for word parsing, and a digraph for analysis of a sentence’s syntax. Furthermore, various rules were defined to solve problems on unknown words while an approach to solve a problem on ambiguous words was devised by constructing a dictionary of ambiguous words as well as considering words surrounding an ambiguous word. The results of word parsing are displayed and evaluated while suggestions are made for a further study and improvement of the PTTSF approach. The PTTSF system can parse words derived from various types of Thai documents, for example, verse, computer advertisements, technical announcements or general documents.
KEYWORD TEXT PARSING / DICTIONARY /UNKNOWN WORD / AMBIGUOUS WORD

 

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