A two-stage model for content determination

  • Authors:
  • Somayajulu G. Sripada;Ehud Reiter;Jim Hunter;Jin Yu

  • Affiliations:
  • Univ. of Aberdeen, Aberdeen, UK;Univ. of Aberdeen, Aberdeen, UK;Univ. of Aberdeen, Aberdeen, UK;Univ. of Aberdeen, Aberdeen, UK

  • Venue:
  • EWNLG '01 Proceedings of the 8th European workshop on Natural Language Generation - Volume 8
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we describe a two-stage model for content determination in systems that summarise time series data. The first stage involves building a qualitative overview of the data set, and the second involves using this overview, together with the actual data, to produce summaries of the time-series data. This model is based on our observations of how human experts summarise time-series data.