Accession Number : ADP001174

Title :   Utilizing Domain-Specific Information for Processing Compact Text,

Corporate Author : NEW YORK UNIV N Y

Personal Author(s) : Marsh,Elaine

Report Date : 01 FEB 1983

Pagination or Media Count : 5

Abstract : This paper identifies the types of sentence fragments found in the text of two domains: medical records and Navy equipment status messages. The fragment types are related to full sentences forms on the basis of the elements which were regularly deleted. A breakdown of the fragment types and their distributions in the two domains is presented. An approach to reconstructing the semantic class of deleted elements in the medical records is proposed which is based on the semantic patterns recognized in the domain.

Descriptors :   *Text processing, *Phrase structure grammars, *Semantics, *Natural language, *Computational linguistics, Symposia, Computer programs, Message processing, Fragments, Syntax, Errors, Input

Distribution Statement : APPROVED FOR PUBLIC RELEASE