IMPLEMENTASI BRILL TAGGER UNTUK MEMBERIKAN POS-TAGGING PADA DOKUMEN BAHASA INDONESIA

Abstract

Part-of-speech (POS) tagging is the process of marking up a word in a text. The aim of this program application is to design a system that is able to proceed POS-Tagging in Indonesian documents by implementing Brill Tagger program. The results showed that of 11.411 words (20 news) used in testing process, 154 words underwent incorrect tagging and 11.257 words were properly labeled according to their part of speech. This indicated that the accuracy of POS-Tagging application program which implemented Brill Tagger Program was 98.65%. The accuracy became 99.75 % after being adapted with lexical and contextual rules.    

 

Keywords:             Brill Tagger, natural language processing, part-of-speech tagging, rule based, transformation based learning