Authors: G. Suresh Kumar; G. Zayaraz
Addresses: Department of Computer Science, Pondicherry University, India ' Department of Computer Science and Engineering, Pondicherry Engineering College, India
Abstract: Question answering systems in general use external knowledge sources for extracting answers. Domain specific question answering systems require pre-constructed knowledge sources like domain ontology. A major challenge in knowledge-based question answering system development is building a huge knowledge base with the objective and correct factual knowledge in the preferred domain. The process of collecting useful knowledge from various sources and maintaining in a knowledge repository is a useful process for providing required answer on demand with greater accuracy and efficiency. In this paper an experimental framework has been proposed for concept-relational ontology-based question answering process. The question answering framework proposed in this paper includes two subsystems: 1) a dynamic concept relational ontology construction module, is capable to extract new concepts from the web and incorporate the extracted knowledge into the concept relational ontology knowledge base; 2) the answer extraction module formulates the query string from the natural language question according to the expected answer and retrieves the information from the ontology for answer formation. Furthermore, a novel statistical validation framework for evaluating the prototype implementation of the proposed question answering system is introduced.
Keywords: question answering systems; knowledge reuse; statistical validation; query driven ontology construction; knowledge-based systems; KBS; concept extraction; knowledge extraction; internet; query strings; natural language questions.
International Journal of Computer Aided Engineering and Technology, 2017 Vol.9 No.3, pp.324 - 336
Received: 05 May 2014
Accepted: 12 Nov 2014
Published online: 27 Mar 2017 *