creators_name: Frey, Miloslaw
type: other
datestamp: 2004-11-20
lastmod: 2011-03-11 08:55:44
metadata_visibility: show
title: Connectionist Taxonomy Learning
ispublished: unpub
subjects: comp-sci-lang
subjects: ling-sem
subjects: comp-sci-mach-learn
subjects: comp-sci-neural-nets
full_text_status: public
abstract: The paper at hand describes an approach to automatise the creation of a class taxonomy. Information about objects, e.g. "a tank is armored and moves by track", but no prior knowledge about taxonomy structure is presented to a connectionist system which organizes itself by means of activation spreading (McClelland and Rumelhart, 1981) and weight adjustments. The resulting connectionist network has a form of a taxonomy sought-after.
date: 2004
date_type: published
refereed: FALSE
referencetext: A. Gomez-Perez and D. Manzano-Macho. A Survey of Ontology Learning Methods and Techniques. Deliverable 1.5, OntoWeb Project, 2003.
J. L. McClelland and D. E. Rumelhart. An interactive activation model of context effects in letter perception: Part 1. An account of basic findings. Psychological Review, 88:375-407, 1981.
E. Rosch. Family resemblance: Studies in the internal structure of categories. Cognitive Psychology, 7:573-605, 1975.
citation:   Frey, Miloslaw  (2004) Connectionist Taxonomy Learning.     (Unpublished)  
document_url: http://cogprints.org/3943/1/categorization.pdf