Named Entity Recognition For Quranic Text Using Rule Based Approaches

Shasha Arzila Tarmizi, Saidah Saad
dx.doi.org/10.17576/apjitm-2022-1102-09

Abstract

The variety and difference between domains for textual data require customization in the Natural Language Processing component especially in Named Entity Recognition where different domains contain several types of entities. The current NER model is deemed not fit to accurately extract entities from Quranic text due to its unique content. This paper describes the building of a rule-based Named Entity Recognition method to extract the entities that exist in the English translation to the meaning of the Quranic text and its performance evaluation. Named entity tagging, a common task in-text annotation, in which entities (nouns) in the unstructured text are identified and assigned a class. A few rules are built to extract several types of entities such as the name of prophets and people, creation, location, time, and the various names of God. The rules are built mainly using regular expressions and gazetteers. The rules that have been built result in high precision and recall as well as a satisfactory F-score of over 90%. The results from this experiment can be used as annotation in building a machine learning model to extract entities from the same type of domain specifically on the Quranic text or generally in the Islamic domain text.

keyword

Named Entity Recognition (NER), rule-based method, Quranic text

Area

Knowledge Technology