earticle

영어

Hadith is everything attributed to Prophet Muhammad Peace Be Upon Him (PBUH) such as says, deeds, explanations, decisions or characteristics of his creation. Each Hadith is composed of two main parts: Isnad and Matn. Isnad processing is one of the unique features of Islam nation, which concentrates on the narrations of the prophet. Before 1400 years, Hadith scholars set the rules and wrote the books to distinguish between the right narrations that really related to the prophet and the lied one. All Hadiths are texts written in Arabic classical language. Processing the Arabic language is a difficult task due to the specificities of this language and the scarcity of the digital resources (grammars, lexicon and corpus). In this paper, we suggest a method for Hadith Isnad processing based on the Multi-Agent approach. We designed and implemented a system composed of five agents, which are: preprocessing agent, lexical agent, morphological agent, replacing agent and syntactical agent. These agents cooperate to analyze Hadith Isnad and to provide the parse tree, Isnad tree and the received method. This system is based on a large database that we created using XML technology to ensure the re-usability, the scalability and the interoperability.