This paper describes how to automatically classify the functional relations from the Factotum knowledge base via a statistical
machine learning algorithm. This incorporates a method for inferring prepositional relation indicators from corpus data. It
also uses lexical collocations (i.e., word associations) and class-based collocations based on the WordNet hypernym relations
(i.e., is-subset-of). The result shows substantial improvement over a baseline approach.
Patrick Cassidy of Micra, Inc. kindly made Factotum available and provided valuable input on the paper. Michael O’Hara helped
much with the proofreading. The first author is supported by a generous GAANN fellowship from the Department of Education.
Some of the work used computing resources at NMSU made possible through MII Grants EIA-9810732 and EIA-0220590.
Factotum is based on the public domain version of Roget’s Thesaurus. The latter is freely available via Project Gutenberg
(http://promo.net/pg), thanks to Micra, Inc.