Detection of Compound Word with Combination Noun and Adjective using Rule Based Technique in Malay Standard Document

Abstract

In this paper we describe our methods for detecting the compound word with combination of Noun and Adjective Compound Nouns in Malay standard document. We addressed the problem on detection of combination noun and adjective in Malay sentences to become a compound word. We modified several identification rules based by using Malay grammar rules and syntactic information to increase the percentage of recall, precision and F1-Score. For compound word identification, we used dictionary-based and thesaurus information for implementing Part of Speech (POS) tagging to all words in the selected Malay document. Testing was done on selected Malay document. The result showed an improvement compared to previous research with a precision of 90.9%, a recall of 10.2% and a F1-Score of 18.1%.