Hostname: page-component-cd9895bd7-hc48f Total loading time: 0 Render date: 2024-12-26T08:01:22.451Z Has data issue: false hasContentIssue false
  • English
  • Français

Choosing the content of textual summaries of large time-series data sets

Published online by Cambridge University Press:  15 February 2006

JIN YU ,
EHUD REITER ,
JIM HUNTER  and
CHRIS MELLISH
JIN YU
Affiliation:
Department of Computing Science, University of Aberdeen Aberdeen AB24 3UE, UK e-mail: jyu@csd.abdn.ac.uk, ereiter@csd.abdn.ac.uk, jhunter@csd.abdn.ac.uk, cmellish@csd.abdn.ac.uk
EHUD REITER
Affiliation:
Department of Computing Science, University of Aberdeen Aberdeen AB24 3UE, UK e-mail: jyu@csd.abdn.ac.uk, ereiter@csd.abdn.ac.uk, jhunter@csd.abdn.ac.uk, cmellish@csd.abdn.ac.uk
JIM HUNTER
Affiliation:
Department of Computing Science, University of Aberdeen Aberdeen AB24 3UE, UK e-mail: jyu@csd.abdn.ac.uk, ereiter@csd.abdn.ac.uk, jhunter@csd.abdn.ac.uk, cmellish@csd.abdn.ac.uk
CHRIS MELLISH
Affiliation:
Department of Computing Science, University of Aberdeen Aberdeen AB24 3UE, UK e-mail: jyu@csd.abdn.ac.uk, ereiter@csd.abdn.ac.uk, jhunter@csd.abdn.ac.uk, cmellish@csd.abdn.ac.uk
Get access Rights & Permissions [Opens in a new window]

Abstract

Natural Language Generation (NLG) can be used to generate textual summaries of numeric data sets. In this paper we develop an architecture for generating short (a few sentences) summaries of large (100KB or more) time-series data sets. The architecture integrates pattern recognition, pattern abstraction, selection of the most significant patterns, microplanning (especially aggregation), and realisation. We also describe and evaluate SumTime-Turbine, a prototype system which uses this architecture to generate textualsummaries of sensor data from gas turbines.

Type
Papers
Information
Natural Language Engineering , Volume 13 , Issue 1 , March 2007 , pp. 25 - 49
Copyright
2006 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)