Addressing Natural Language Request Complexity: At Semantic Web Service Discovery Horizon

Abstract

The wondrous influence of semantic web on Service-Oriented Architecture pushes it towards a realistic and self-driven architecture where publication, discovery, selection, composition, and monitoring of services are semi-automatically performed on the behalf of their hosts or mediators. In the direction of this realistic and self-driven architecture, this research work is adding one more realistic aspect of 'interpretation of natural language request' to making the service discovery more usable for novice users. Three contributions have been made: (1) description of natural language request using six-slab range (2) two algorithms for extraction, sub-request generation, inclusion of semantics and semantic matchmaking of natural language request, and (3) evaluation of proposed strategy with two semantic formalisms. The proposed algorithms handle each complex service request as an individual entity and extract the demand/s of the request by decomposing it to the simple request from conjunction, condition, and negation-oriented natural language request. The experimental evaluation of the proposed strategy signifies the given algorithms. The proposed work and result evaluation is a part of on-going research on a generic discovery mechanism for semantic web services.