Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.11889/1268
Title: Advanced matching function towards linking Arabic ontology with the English WordNet
Other Titles: خوارزمية ربط مفاهيمي نحو ربط آلي بين المفاهيم العربية و الإنجليزية
Authors: Melhem, Mohammed M.
Keywords: Arabic language - Machine translating
English language - Machine translating
Arabic language - Translating into English
English language - Translating into Arabic
Machine translating
Issue Date: 2012
Publisher: Birzeit University
Abstract: The major challenge in constructing an Arabic ontology is that it needs many resources, manual work, and semi-manual techniques that require creating a sophisticated tool to ease the process. Such tool should provide the technique and ability to link and benefit from other existing linguistic resources. This tool will be used to link between concepts from different multilingual resources, based on a concept matching function. The matching function is an algorithm that was developed In Birzeit University, by undergraduate students. It maps Arabic concepts in the Arabic Ontology with their equivalent concepts in the English WordNet. The existing function carries a certain level of tolerance, but suffers from some limitations in the matching process as it uses fixed parameters. These parameters are categorized into two main categories of weighing parameters that include; Keyword, Super Type, Sub-type, and Synonyms as its main parts. The second category is the expansion levels of processed data by this function. This thesis introduces a novel approach to enhance the matching function, by increasing the accuracy of matching operation, minimizing the resulted errors, and increasing the performance of the algorithm. The presented solution utilizes machine-learning approach to configure and tune the mentioned parameters. The followed methodology resulted in an enhancement on the matching operation, where the overall accuracy for the top 15 matched concepts in the enhanced matching function represented in 55% compared to 41% achieved by old version of the matching function, showing a 14% of improvement.
URI: http://hdl.handle.net/20.500.11889/1268
Appears in Collections:Theses

Files in This Item:
File Description SizeFormat 
thesis_05032016_995.pdf1.85 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.