International Journal of Computer Science Issues

More than a traditional journal...

Named Entity Recognition is a task in Information Extraction. Named entity recognition is become very important for natural language processing. Named entity recognition is the detection and classification of entities from the unstructured text, for the Arabic language named entity recognition is new in natural language processing although it has progressed in other languages such as English language. Named entity recognition researchers has become interested in recent years for Arabic natural language processing, that is due to named entity recognition plays an essential role for the information extraction systems and question answering systems. In this paper, we designed system that is enhance named entities recognition for Arabic language, the system develops for Arabic nouns extraction and entities extraction, the nouns extraction system is based on Arabic morphological and the nouns extraction system using no gazetteers, the system is combined with entities extraction system depending gazetteers, the system extracts nouns according to morphological Arabic and classify 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 using classifying entities annotation in the text the second way is adding entities tagset in the text. The system achieves results in an average recall of 84%.