We present an automatic approach to learning criteria for classifying the parts-of-speech used in lexical mappings. This will further automate our knowledge acquisition system for non-technical users. The criteria for the speech parts are based on the types of the denoted terms along with morphological and corpus-based clues. Associations among these and the parts-of-speech are learned using the lexical mappings contained in the Cyc knowledge base as training data. With over 30 speech parts to choose from, the classifier achieves good results (77.8% correct). Accurate results (93.0%) are achieved in the special case of the mass-count distinction for nouns. Comparable results are also obtained using OpenCyc (73.1% general and 88.4% mass-count). Collection: PhysicalDeviceMicrotheory: ArtifactGVocabularyMt isa: ExistingObjectType genls: Artifact ComplexPhysicalObject SolidTangibleProduct Microtheory: ProductGMt isa: ProductType

No abstract

Machine learning systems (MLS) that model low-level processes are the cornerstones of current AI systems. These 'indirect' learners are good at classifying kinds that are distinguished solely by their manifest physical properties. But the more a kind is a function of spatio-temporally extended properties -words, situation-types, social norms -the less likely an MLS will be able to track it. Systems that can interact with objects at the individual level, on the other hand, and that can sustain this interaction, can learn responses to increasingly abstract properties, including representational ones. This representational capacity, arguably the mark of intelligence, then, is not available to current MLS's.

No abstract