Ontology Construction Based on Latent Topic Extraction in a Digital Library

Abstract

This paper discusses the automatic ontology construction process in a digital library. Traditional automatic ontology construction uses hierarchical clustering to group similar terms, and the result hierarchy is usually not satisfactory for human’s recognition. Human-provided knowledge network presents strong semantic features, but this generation process is both labor-intensive and inconsistent under large scale scenario. The method proposed in this paper combines the statistical correction and latent topic extraction of textual data in a digital library, which produces a semantic-oriented and OWL-based ontology. The experimental document collection used here is the Chinese Recorder, which served as a link between the various missions that were part of the rise and heyday of the Western effort to Christianize the Far East. The ontology construction process is described and a final ontology in OWL format is shown in our result.KeywordsDigital LibraryLatent Dirichlet AllocationLatent Semantic AnalysisDomain OntologyOptical Character RecognitionThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.