Arabic Cooperative Answer Generation via Wikipedia Article Infoboxes

Abstract

[EN] The typical question-answering system is facing many challenges related to the processing of questions and information resources in the extraction and generation of adequate answers. These challenges increase when the requested answer is cooperative and its language is Arabic. In this paper, we propose an original approach to generate cooperative answers for user-definitional questions designed to be integrated in a question-answering system. This approach is mainly based on the exploitation of the semi-structured Web knowledge which consists in using features derived from Wikipedia article infoboxes to generate cooperative answers. It is globally independent of a particular language, which gives it the ability to be integrated in any definitional question-answering system. We have chosen to integrate and experiment it in a definitional question-answering system dealing with the Arabic language entitled DefArabicQA. The results showed that this system has a significant impact on the approach efficiency regarding the improvement of the quality of the answer.