Using an Arabic Ontology to Improve the Q/A Task

Abstract:

Users in an open environment such as the Web need advanced tools which make easier the access to the information. Question/Answering systems are new types of Information Retrieval (IR) systems. They reduce the effort to be done by users when searching for a precise answer to a question instead of a set of documents. In this paper, we describe our project of improving the Arabic Q/A task by using ontologies in the semantic Query Expansion (QE) approach that we propose. We present the steps that we followed in the preparation of our semantic resource and the experiments related to the evaluation stage as well.

nsdlogo2016