Extraction des relations sémantiques à partir du Wiktionnaire Arabe

Abstract

Electronic language resources play a very important role in natural language processing. They are used in several linguistic applications including machine translation, text indexing, automatic summary…etc. The aim of this paper is to create a lexical database for the Arabic language that does not have many of these resources. We exploit web resources like Wikipedia and Wiktionary, which have become an interesting websites for extracting information. In this work, we seek to automatically extract semantic relationships such as synonyms and antonyms from Wiktionary Arabic.

Keywords: Lexical base, Information retrieval, Semantic relations, Arabic language,Wiktionnaire, Wikipédia