Modifying a natural language processing system for European languages to treat Arabic in information processing and information retrieval applications

Abstract

The goal of many natural language processing platforms is to be able to someday correctly treat all languages. Each new language, especially one from a new language family, provokes some modification and design changes. Here we present the changes that we had to introduce into our platform designed for European languages in order to handle a Semitic language. Treatment of Arabic was successfully integrated into our cross language information retrieval system, which is visible online.