Computational Recognition of literary forms and its Transformation to a Literature Ontology: an Experiment on Quran

Main Article Content

Aliabbas Petiwala
S.Siva Sathya

Abstract

The Quran being a literary masterpiece in Arabic, employs a versatile gamut of rhetorical features, literary forms and figures of speech not present in any other rhymed prose, past or present. Linguistic Scholars have meticulously enumerated and classified hundreds of figures of speech. The degree and count of figures of speech employed in a piece of natural language text can give a useful insight to the degree of literary excellence of the given text. Thus it is required to first computationally identify an assortment of figures of speech present in the literature text. Computational recognition of various figures of speech can help us quantify the literary excellence score as a function of the absolute counts of the literary features and figures of speech. This paper presents various Lexico-syntactic patterns to recognize important literary forms. The English translation of the Quran was chosen as a gold standard in the experiments owing to its rich literary composition. These literary forms are then modeled as a literary ontology in OWL web ontology language and can be harnessed by semantic web applications.

 

 

Keywords: Computational Linguistics, Literary Forms, Ontology, Semantic Web, Quran, Islam, Text Mining.

Downloads

Download data is not yet available.

Article Details

Section
Articles