Assessing Semantic Similarity Measures and Proposing a WuP-Resnik Hybrid Metric for Enhanced Arabic Language Processing.

The accurate quantification of semantic similarity among Arabic words presents a significant challenge in Natural Language Processing (NLP). This is a critical aspect for a wide array of text-centric applications, including recommendation systems, plagiarism detection, and information retrieval. Enhanced performance in searches and classification is achieved by simplifying concepts within machine processing and unifying words with close meanings. This research investigates the complexities of measuring semantic similarity in Arabic, a language with distinct features such as the absence of short vowels in written text that renders distinguishing words without vowel diacritics challenging for computing systems. The effectiveness of various semantic similarity metrics is meticulously evaluated in this study, with a specific focus on their applicability to Arabic WordNet and English WordNet. The challenges associated with using Arabic WordNet for measuring word similarity are illuminated, and an innovative metric, integrating the Wu- Palmer and Resnik metrics, is proposed to enhance result accuracy. The primary accomplishment of this research resides in the identification of an optimal semantic similarity metric with a reduced error rate, thereby boosting the precision of results in NLP. This pivotal advancement paves the way for more accurate semantic assessments and improved performance across a broad spectrum of applications. [ABSTRACT FROM AUTHOR]

Copyright of Revue d'Intelligence Artificielle is the property of International Information & Engineering Technology Association (IIETA) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)