SIMPLIFICATION OF RETRIEVAL REQUESTS GENERATION BY QUESTION-ANSWERING SYSTEMS.

Research output: Contribution to conferencePaper

Abstract

Description of a system for answering English questions about a relational data base. The data base consists of narrative medical records which have been automatically reduced to a tabular form called an information format. Like other question-answering systems, this operates in three stages: syntactic analysis; semantic interpretation, which generates retrieval requests similar to predicate calculus expressions; and retrieval. This focuses on a simplification procedure which is applied to the output of the semantic interpreter in order to simplify the retrieval request. The simplification rules are described in detail and contrasted with other relational data base optimization procedures.

Original languageEnglish (US)
Pages400-406
Number of pages7
StatePublished - Jan 1 2017
EventInt Conf on Very Large Data Bases, 4th, Proc - W Berlin, W Ger
Duration: Sep 13 1978Sep 15 1978

Other

OtherInt Conf on Very Large Data Bases, 4th, Proc
CityW Berlin, W Ger
Period9/13/789/15/78

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'SIMPLIFICATION OF RETRIEVAL REQUESTS GENERATION BY QUESTION-ANSWERING SYSTEMS.'. Together they form a unique fingerprint.

  • Cite this

    Grishman, R. (2017). SIMPLIFICATION OF RETRIEVAL REQUESTS GENERATION BY QUESTION-ANSWERING SYSTEMS.. 400-406. Paper presented at Int Conf on Very Large Data Bases, 4th, Proc, W Berlin, W Ger, .