Identification of Ambiguous Sentence Pattern in Indonesian Using Shift-Reduce Parsing

Abstract

In a sentence writing, mistakes often happened unconsciously by the writers that caused a sentence has double meaning. This research developed a software that can identify the pattern of ambiguous sentences in Bahasa using Shift Reduce Parsing. Input for this software is a single sentence in Bahasa. This research involved three preprocessing namely case folding, tokenizing, and Part of Speech (POS) Tagging. Then the result of preprocessing used in identifying ambiguous sentence. In the process of identifying ambiguous sentences, Shift Reduce Parsing used to the parsing’s result of a sentence. As the result, this software that can differentiate whether if it is an ambiguous sentence or not. Accuracy of identifying the pattern of ambiguous sentence in Bahasa using Shift Reduce Parsing reaches 83%.