Named entity recognition for Psychological domain: Challenges in document annotation for the Arabic Language

Abstract

The named entity extraction to improve not only the keyword search but become an essential element for semantic annotation and it opened the door for recognition of medical named entities which is a difficult task for the extraction of information and understanding of the natural language. Considerable work has been done for the semantic annotation of the biomedical text, in particular English, thanks to the variety of tools available for this language. In this article we propose an approach for the semantic annotation of psychological texts in Arabic based on the named entity. Two techniques were applied for the recognition processes: the first requirement prior to the technique was completely dependent on direct identification with the utilization of gazetteers and the second technique is a rule-based model in which rules are techniques were put constructed on the basis of a gazetteers list. Experiments yield the overall Fmeasure values of 86,407.