A MORPHOLOGICAL ANALYSIS OF MALAY TRANSLATED QUR’AN CORPUS

Abstract

Research in Natural Language Processing for English has shown successful results for more than a decade. However, it is difficult to adapt those techniques to the Malay language, because its complex morphology and orthographic forms are very different from English. Moreover, limited resources and tools for computational linguistic analysis are available for Malay. This study aims to demonstrate the use of Malay morphological analysis on the Malay translated Qur’an, for research and teaching purposes. To present the use of Malay morphological analysis, we propose a morphological analysis algorithm for the Malay-translated Qur’an that allows it to be created, discovered, and queried. This involved the creation of the first Malay-translated Qur’an corpus of 149,654 words with root word annotation and a new morphological analysis algorithm for Malay-translated Qur’an. Besides, a new list of Malay Stop words, a new rule-based stemming algorithm, and a new root word annotation were developed. This new Malay language resource will benefit other researchers, especially in religious morphological analysis and semantic modelling in research related to Malay documents.