doi: 10.4304/jsw.1.1.40-50
On-the-fly Construction of Web Services Compositions from Natural Language Requests
- 1 Politecnico di Torino, Torino, Italy
- 2 IBM T.J. Watson Research Center, Hawthorne, NY, USA and Telecom Italia Lab, Torino, Italy
- 3 Telecom Italia Lab, Torino, Italy
Abstract
The introduction of Semantic Web techniques inService-oriented Architectures enables explicitrepresentation and reasoning about semantically richdescriptions of service operations. Those techniques holdpromise for the automated discovery, selection, compositionand binding of services. This paper describes an approachto derive formal specifications of Web Service compositionson the basis of the interpretation of informal user requestsexpressed in restricted Natural Language. Our approachleverages the semantic and ontological description of aportfolio of known service operations (called the SemanticService Catalog). Each user request is processed against aNatural Language vocabulary that includes lexicalconstructs designed to convey the operations' semantics, inorder to recognize and extract fundamental functionalrequirements implied by the request, and associate them toentries in the Catalog. In addition, the request interpreterextracts from the request the overall service logic, expressedin terms of a set of modular templates describing controland data flow among the selected operations. The result is acomposition specification that associates on demand eachuser request to a new composed service. That specification isformal and can thus be transformed in an executable flowdocument for a target service composition engine.
Keywords
- Service-Oriented Architectures
- Semantic
How to Cite
Alessio Bosca, Fulvio Corno, Giuseppe Valetto, and Roberta Maglione, "On-the-fly Construction of Web Services Compositions from Natural Language Requests," Journal of Software, vol. 1, no. 1, pp. 40-50, 2006. https://doi.org/ 10.4304/jsw.1.1.40-50
Copyright & License
Copyright © 2006 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).