Please use this identifier to cite or link to this item: https://ptsldigital.ukm.my/jspui/handle/123456789/475574
Title: Word sense disambiguation based on semantic similarity measurements in English translation of holy Quran
Authors: Sarah Abdul-Ameer Mussa (P69603)
Supervisor: Sabrina Tiun, Dr.
Keywords: Word sense disambiguation
Word sense
Semantic similarity
English translation
Quran
Al-Quran
Universiti Kebangsaan Malaysia -- Dissertations
Issue Date: 23-Mar-2015
Description: Word sense disambiguation (WSD) is identified as an open problem which associates to natural language processing within computational linguistics. Disambiguation manages the identification process pertaining to the utilization of the word within a sentence in the event that the word incorporates several meanings. The problem of WSD can be solved by making the best possible choice from several different meanings of words, which otherwise cause ambiguity and confusion. WSD on Quranic text is challenging because it heavily relies on the semantic relatedness in meanings. This research proposes a system for measuring similarity between words within the Holy Quran that have been translated into the English language. The proposed system is based on a combination of three traditional semantic similarity measurements, which are Wu-Palmer (WUP), Lin (LIN) and Jiang-Conrath (JCN). The Wu- Palmer technique measures similarity by considering the depth of the two synsets in the Wordnet taxonomies, along with the depth of lowest common subsumer (LCS). The Jiang-Conrath and Lin techniques use the notion of information content (IC), which is a measure of specificity of a concept. In addition, this study has enhanced these measurements by making use of extensive semantic knowledge from sources, such as Wordnet, to detect the meaning of the individual words. This study has validated the efficiency of the proposed model by using different Ayahs from the Holy Qur‟an, which were translated by the popular translator Yusuf Ali. Initially, the data sets were tested with each of these three measurements, and were then tested on the combination of the all three measurements. This experiment was performed to obtain the best overall similarity score. The empirical results demonstrate that the combination of the three mentioned semantic similarity techniques obtained competitive results when compared with using individual similarity measurements.,Master/Sarjana
Pages: 99
Publisher: UKM, Bangi
Appears in Collections:Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Files in This Item:
There are no files associated with this item.


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