A scheme-driven natural language query translator

  • Authors:
  • David W. Embley;Roy E. Kimbrell

  • Affiliations:
  • Brigham Young University, Provo, Utah;Planning Research Corporation, Bellevue, Nebraska

  • Venue:
  • CSC '85 Proceedings of the 1985 ACM thirteenth annual conference on Computer Science
  • Year:
  • 1985

Quantified Score

Hi-index 0.00

Visualization

Abstract

An approach to natural language query translation is presented that is driven mainly by the semantics contained in an extended database scheme. This approach has the advantage of ease of implementation and thus portability since the scheme can easily be extended to interface with the translation system's natural language understanding modules. The required extensions consist of adding domain specific routines to recognize and classify literals and a lexicon to recognize context keywords. The results from these recognizers are then presented to a domain independent translator for further analysis. A prototype system has been implemented and some initial experimentation has been done. Observations about the effectiveness of the translator and its efficiency are reported.