Using OLAP and Data Mining for Content Planning in Natural Language Generation

  • Authors:
  • Eloi L. Favero;Jacques Robin

  • Affiliations:
  • -;-

  • Venue:
  • NLDB '00 Proceedings of the 5th International Conference on Applications of Natural Language to Information Systems-Revised Papers
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a new approach to content determination and discourse organization in Natural Language Generation (NLG). This approach relies on two decision-support oriented database technologies, OLAP and data mining, and it can be used for any NLG application involving the textual summarization of quantitative data. It improves on previous approaches to content planning for NLG in quantitative domains by providing: (1) application domain independence, (2) efficient, variable granularity insight search in high dimensionality data spaces, (3) automatic discovery of surprising, counter-intuitive data, and (4) tailoring of output text organization towards different, declaratively specified, analytical perspectives on the input data.