The simplification of retrieval requests generated by question-answering systems

  • Authors:
  • Ralph Grishman

  • Affiliations:
  • -

  • Venue:
  • VLDB '78 Proceedings of the fourth international conference on Very Large Data Bases - Volume 4
  • Year:
  • 1978

Quantified Score

Hi-index 0.00

Visualization

Abstract

We describe 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, ours operates in three stages: syntactic analysis; semantic interpretation, which generates retrieval requests similar to predicate calculus expressions; and retrieval. This paper 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.