A Rule-Based Entities Recognition System for Modern Standard Arabic

The Named Entity Recognition (NER) is a task in Information Extraction (IE). The Named entity recognition has become very important for natural language processing. The named entity recognition is defined as the detection and classification of entities from un-structured text where for the Arabic language, the named entity recognition is new in the natural language processing although it has progressed in other languages such as English language. The named entity recognition researchers have become of great interest in recent years for Arabic natural language processing because the named entity recognition plays an essential role for both the information extraction systems and the question answering systems. In this paper, we designed a system which enhanced the named entities recognition for Arabic language where the system was developed for Arabic nouns and entities extractions. The nouns extraction system is based on Arabic morphological which uses no gazetteers where the system is combined with entities extraction system depending on gazetteers. The systems extracts nouns according to morphological Arabic and classify them into: person name entities, title entities, countries entities, cities entities, nationality entities, date and time entities for open text. The system extracts entities in the modern standard Arabic text by two ways: the first way is through using classifying entities annotation in the text; and the second way is through adding entities tag set in the text. The system achieves results in an average recall of 84%.