Kathleen Dahlgren

Learn More
This paper describes a method using commonsense knowledge for discarding spurious syntactic ambiguities introduced by post-verbal prepositional phrase attachment during parsing. A completely naive parser will generate three parses for sentences of the form NP-V-Det-N-PP. The prepositions alone are insufficiently precise in meaning to guide selection among(More)
Support for the prototype theory of categorization was found i n a study of the structure of social categories. Though occupational terms such as DOCTOR are socially defined, they do not have the classical structure their clear definitional origins would predict. Conceptions of social categories are richer and more complex than those of physical object(More)
KT encodes commonsense knowledge (CK) about entities and relations in a cross-classified Ontology and a database of generic (prototypical and inherent) information. The verb Ontology combines linguistic and psycholinguistic classification. The generic information for verbs encodes typical associations with actions and events. This knowledge base is useful(More)
Intelligent Text Processing is a small start-up company participating in the MUC-3 exercise fo r the first time this year. Our system, Interpretext, is based on a prototype text understandin g system. With three full-time and three part-time people, dividing time between MUC-3 and othe r contract projects, ITP made maximum use of modest resources. ITP's(More)
The ITP System for MUC3 is diagrammed in Figure 1. The three major modules handle different units of processing : the Message Handler processes a message unit; the ITP NLU Module processes a sentence and builds a Cognitive Model of the message ; and the MUC3 Templat e Reasoning Module processes a segment of discourse. The Message Handler identifies an(More)