Interpreting Natural Language

An automated clinical record system must have the following characteristics: as far as the physician is concerned it must operate in natural language on standard sized paper; it must be able to accept information from the physician at a time when he is oriented to clinical terminology and a clinical mode of thinking; it must have an output which is clinically useful for the care and management of a patient; each item of information must be addressable so that it may act as an index for scientific information retrieval; it must be capable of accepting quantative and natural language information.Clinical information constitutes a mathematical set, only a few members of which are applicable to any particular clinical situation, and to which new members are constantly being added. The members of this set are seldom mutually exclusive. An acceptable system which is capable of processing this type of information has been designed utilizing the concepts of self-encoding forms and variable-field, variable-length records. Applications of these principles will expedite hospital automation, the establishment of drug evaluation information systems, and of regional and nationwide medical record systems.

Download Full-text

The Distinction between Linguistic and Conceptual Semantics in Medical Terminology and its Implication for NLP-Based Knowledge Acquisition

Methods of Information in Medicine ◽

10.1055/s-0038-1634568 ◽

1998 ◽

Vol 37 (04/05) ◽

pp. 327-333 ◽

Cited By ~ 3

Author(s):

F. Buekens ◽

G. De Moor ◽

A. Waagmeester ◽

W. Ceusters

Keyword(s):

Natural Language ◽

Knowledge Acquisition ◽

Natural Language Understanding ◽

Knowledge Bases ◽

Linguistic Knowledge ◽

Medical Terminology ◽

Language Understanding ◽

Conceptual Semantics

AbstractNatural language understanding systems have to exploit various kinds of knowledge in order to represent the meaning behind texts. Getting this knowledge in place is often such a huge enterprise that it is tempting to look for systems that can discover such knowledge automatically. We describe how the distinction between conceptual and linguistic semantics may assist in reaching this objective, provided that distinguishing between them is not done too rigorously. We present several examples to support this view and argue that in a multilingual environment, linguistic ontologies should be designed as interfaces between domain conceptualizations and linguistic knowledge bases.

Download Full-text