Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476632
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Nazlia Omar, Assoc. Prof. Dr. | |
dc.contributor.author | Mona Mohamed Ali Ahmed Asharef (P49070) | |
dc.date.accessioned | 2023-10-06T09:22:50Z | - |
dc.date.available | 2023-10-06T09:22:50Z | - |
dc.date.issued | 2011-08-01 | |
dc.identifier.other | ukmvital:122214 | |
dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476632 | - |
dc.description | Named entity recognition (NER) systems aim to determine and classify automatically the proper nouns, such as names of people, names of locations, dates and time indications, and events in texts. NER systems play a significant role in many areas of Natural Language Processing (NLP) such as question answering systems, text summarization, text classification, information retrieval, information extraction systems and machine translation. Many researchers have attempt to solve this problem in a variety of languages, but only few limited researches have focused on NER for Arabic language. All previous Arabic named entity recognition systems have been built to extract the named entities from several text types. The goal of this research is to design and develop Arabic named entity recognition system in the crime domain. We identify five types of named entities; people, location, organization, date and time. We used rule-based approach to identify the names of entities in crime documents. We produced our corpus by choosing crime documents from Arabic news papers and tagged them by using an automatic tagger (HVMM POS) and we used this corpus as an input for our system. The rules are constructed based on part of speech (POS) tags of the input texts and word lists which consists of indicative verbs and important keywords. In addition, the Gazetteer, which is a dictionary of names, is also used in the development of the rules. The accuracy of the result of our system is 90% which it indicates that the rule based is effective method and the performance of the achieved system is satisfactory.,Master of Information Technology,Certification of Master's / Doctoral Thesis" is not available" | |
dc.language.iso | eng | |
dc.publisher | UKM, Bangi | |
dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
dc.rights | UKM | |
dc.subject | Natural language processing (Computer science) | |
dc.subject | Arabic language -- Data processing | |
dc.subject | Universiti Kebangsaan Malaysia -- Dissertations | |
dc.subject | Dissertations, Academic -- Malaysia | |
dc.title | Rule based Arabic named entity recognition for crime documents | |
dc.type | theses | |
dc.format.pages | 110 | |
dc.identifier.callno | QA76.9.N38A834 2012 3 tesis | |
dc.identifier.barcode | 005608 (2021) | |
Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ukmvital_122214+SOURCE1+SOURCE1.0.PDF Restricted Access | 13.89 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.