Thesis (M.Sc.) - Cairo University - Faculty of Computers and Information - Department of Computer Science

Named entity recognition (NER) is currently an essential research area that supports many tasks in natural language processing (NLP). Its goal is to find a solution to improve the accuracy of named entities identification. There are many application of NLP depending on NER such information retrieval (IR), machine translation (MT), question answering (QA), etc. Several models were widely used for NER such as: Ruled based, machine learning (ML), and hybrid models. Different techniques were applied for NER, for example, in ML conditional random fields (CRF), support vector machine (SVM), and maximum entropy (ME) have been considered as mostly used techniques. Arabic language has a special orthography and a complex morphology which bring new challenges to the NER task to be investigated. Several researchers studied Arabic NER in order to achieve high accuracy as well as giving a detailed error analysis and results discussion so as to make the study beneficial to the research community. This work presents an integrated model for Arabic named entity recognition (ANER) problem. The basic idea of that model is to combine linguistic rules, ML based techniques and semantic features of Arabic language in order to enhance the accuracy of ANER. The proposed model focused on recognizing three types of named entities: person, organization and location. The basic idea of that model is to combine several linguistic features and to utilize syntactic dependencies to infer semantic relations between named entities

Issued also as CD