Latent Semantic Analysis - The Dynamics of Semantics Web Services Discovery

Semantic Web Services (SWS) have currently drawn much momentum in both academia and industry. Most of the solutions and specifications for SWS rely on ontology building, a task needs much human (e.g. domain experts) involvement, and hence cannot scale very well in face of vast amount of web information and myriad of services providers. The recent proliferation of SOA applications exacerbates this issue by allowing loosely-coupled services to dynamically collaborate with each other, each of which might maintain a different set of ontology. This chapter presents the fundamental mechanism of Latent Semantic Analysis (LSA), an extended vector space model for Information Retrieval (IR), and its application in semantic web services discovery, selection, and aggregation for digital ecosystems. First, we explore the nature of current semantic web services within the principle of ubiquity and simplicity. This is followed by a succinct literature overview of current approaches for semantic services/software component (e.g. ontology-based OWL-s) discovery and the motivation for introducing LSA into the user-driven scenarios for service discovery and aggregation. We then direct the readers to the mathematical foundation of LSA - SVD of data matrices for calculating statistics distribution and thus capturing the `hidden' semantics of web services concepts. Some existing applications of LSA in various research fields are briefly presented, which gives rise to the analysis of the uniqueness (i.e. strength, limitations, parameter settings) of LSA application in semantic web services. We provide a conceptual level solution with a proof-of-concept prototype to address such uniqueness. Finally we propose an LSA-enabled semantic web services architecture fostering service discovery, selection, and aggregation in a digital ecosystem.

[1]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[2]  John Caron,et al.  Experiments with LSA scoring: optimal rank and basis , 2001 .

[3]  Peter W. Foltz,et al.  An introduction to latent semantic analysis , 1998 .

[4]  Amit P. Sheth,et al.  Semantic Web Services, Processes and Applications (Semantic Web and Beyond: Computing for Human Experience) , 2006 .

[5]  Paul Horst,et al.  Factor analysis of data matrices , 1965 .

[6]  Yanchun Zhang,et al.  Advanced Web Technologies and Applications , 2004, Lecture Notes in Computer Science.

[7]  Garrison W. Cottrell,et al.  Latent semantic indexing is an optimal special case of multidimensional scaling , 1992, SIGIR '92.

[8]  Muhammad Ahtisham Aslam,et al.  Applying Semantics (WSDL, WSDL-S, OWL) in Service Oriented Architectures (SOA) , 2007 .

[9]  Michael W. Berry,et al.  Large-Scale Sparse Singular Value Computations , 1992 .

[10]  Richard Kittredge,et al.  Sublanguage : studies of language in restricted semantic domains , 1982 .

[11]  Yanchun Zhang,et al.  Algorithm for web services matching , 2004 .

[12]  Elizabeth R. Jessup,et al.  Matrices, Vector Spaces, and Information Retrieval , 1999, SIAM Rev..

[13]  Bob Rehder,et al.  How Well Can Passage Meaning be Derived without Using Word Order? A Comparison of Latent Semantic Analysis and Humans , 1997 .

[14]  Peter M. Wiemer-Hastings,et al.  How Latent is Latent Semantic Analysis? , 1999, IJCAI.

[15]  Subbarao Kambhampati,et al.  A snapshot of public web services , 2005, SGMD.

[16]  John R. Skoyles Meaning and context: the implications of LSA (latent semantic analysis) for semantics. , 2002 .

[17]  Ewan D. Tempero,et al.  A Java reuse repository for Eclipse using LSI , 2006, Australian Software Engineering Conference (ASWEC'06).

[18]  C. Eckart,et al.  The approximation of one matrix by another of lower rank , 1936 .

[19]  John G. Lewis,et al.  Sparse matrix test problems , 1982, SGNM.

[20]  Susan T. Dumais,et al.  Improving the retrieval of information from external sources , 1991 .