Title :
Unsupervised semantic annotation of Web service datatypes
Author :
Emil Şt. Chifu;Ioan Alfred Letia
Author_Institution :
Department of Computer Science, Technical University of Cluj-Napoca, Romania
Abstract :
The paper describes an unsupervised model for classifying Web service datatypes into a large number of classes specified by an ontology. As a result of the classification, each datatype component of a Web service is associated to one ontology concept, the name of which is further used to semantically annotate the datatype. The framework is based on an extended model of hierarchical self-organizing maps. For the machine learning process, the datatypes, i.e. the input/output messages of the web services, are encoded in a bag-of-words manner, by taking into account the words that occur in their WSDL description. This is actually a vector space representation of the datatype messages. We experimented this automatic semantic annotation model with the SAWSDL-TC service retrieval test collection, a data set used as a benchmark for evaluating the performance of SAWSDL service matchmaking algorithms. The taxonomy and the service datatypes to be classified in our experiments are collected from this dataset.
Keywords :
"Support vector machine classification","Neurons","Classification algorithms","Training","Taxonomy","Artificial neural networks","Web services"
Conference_Titel :
Intelligent Computer Communication and Processing (ICCP), 2010 IEEE International Conference on
Print_ISBN :
978-1-4244-8228-3
DOI :
10.1109/ICCP.2010.5606464