Inferring parts of speech for lexical mappings via the Cyc KB

Abstract

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

Emotionally Driven Natural Language Generation for Personality Rich Characters in Interactive Games

“…Due to the lack of an explicit grammar along with a limited ontology, our system can be overgenerative-it will produce very similar if not identical sentences within a small span of time. One way we can solve this problem is to expand the knowledge base to use an existing system (OHara et al 2004), to increase the vocabulary and understanding capability of the characters.…”