Temporal inferences in medical texts
Klaus K. Obermeier · 1985
The objectives of this paper are twofold, whereby the computer program is meant to be a particular implementation of a general natural language [NL] processing system [NLPS] which could be used for different domains. The first objective is to provide a theory for processing temporal information contained in a well-structured, technical text. The second objective is to argue for a knowledge-based approach to NLP in which the parsing procedure is driven by extra linguistic knowledge.The resulting computer program incorporates enough domain-specific and general knowledge so that the parsing procedure can be driven by the knowledge base of the program, while at the same time employing a descriptively adequate theory of syntactic processing, i.e., X-bar syntax. My parsing algorithm not only supports the prevalent theories of knowledge-based parsing put forth in AI, but also uses a sound linguistic theory for the necessary syntactic information processing.