Xavier Polanco

Instantiation of Relations for Semantic Annotation

This paper presents a methodology for the semantic annotation of Web pages with individuals of a domain ontology. While most semantic annotation systems can recognize knowledge units, they usually do not establish explicit relations between them. The method presented identifies the individuals which should be related among the whole set of individuals and codes them as role instances within an OWL ontology. This is done by using a correspondence between the tree structure of a Web page and the semantics of the information it contains

Artificial neural network technology for the classification and cartography of scientific and technical information

This paper describes the implementation of multivariate data analysis: NEURODOC applies the axial k-means method for automatic, non-hierarchical cluster analysis and a Principal Component Analysis (PCA) for representing the clusters on a map. We next introduce Artificial Neural Networks (ANNs) to extend NEURODOC into a neural platform for the cluster analysis and cartography of bibliographic data. The ANNs tested are: the Adaptive Resonance Theory (ART 1), a Multilayer Perceptron (MLP), and an associative network with unsupervised learning (KOHONEN). This platform is intended for quantitative analysis of information.

A computer system for big scientometrics at the age of the World Wide Web

A computer system combining hypertext and database management technologies is shown to be appropriate with the goals of information analysis. Such a system, HENOCH, designed to easily store any SGML document in a relational database, and to make these data accessible via the World Wide Web is exemplified in the particular case where the stored data is the result of clustering and mapping tools on bibliographic data. The software features of this system (genericity, reusability, extensibility) are explained and justified by the use of the SGML tree structure and the encapsulation of creation and manipulation functions of the relational database management system (RDBMS). The interest of WWW-RDBMS-based user interface is demonstrated by two complementary types of navigation for information analysis: an intuitive exploration mode based on the map metaphor and an assisted searching mode based on the “Who does What, and Where, with Whom” metaphor.