Concept Search Tool for Multilingual Hadith Corpus

Samah Mohamed Osman Hassan, Eric Atwell

Abstract: The search for the Hadith and understanding of the concepts and meaning is the important science. Moreover searching using concepts is a technique used with large data and purpose to obtain relevant results and more accurate. Accordingly the idea of building a search tool for Hadith by concepts to facilitate searches for users on the Web and make the Hadith is available in several ways. In this paper, we will design a concept search tool for Hadith. Our plan to work in three phases the first phase is select the dataset from Ahadith in Sahih Bukhari and define the concepts which will be extracted from the same book. Sahih Bukhari book is contains 100 concept (book). Second phase generation of (HTML) files, each page will contain one Hadith text with four languages Arabic, English, French, Russian, plus its concepts. The third phase builds a website to contain this tool.

Keywords: Concept, Hadith, Multilingual, Parallel corpora, Tree Concept