Selecting the content of textual descriptions of geographically located events in spatio-temporal weather data

Ross Turner, Gowri Somayajulu Sripada, Ehud Baruch Reiter, Ian P. Davy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In several domains spatio-temporal data consisting of references to both space and time are collected in large volumes. Textual summaries of spatio-temporal data will complement the map displays used in Geographical Information Systems (CIS) to present data to decision makers. In the RoadSafe project we are working on developing Natural Language Generation (NLG) techniques to generate textual summaries of spatio-temporal numerical weather prediction data. Our approach exploits existing video processing techniques to analyse spatio-temporal weather prediction data and uses Qualitative Spatial Reasoning(QSR) techniques to reason with geographical data in order to compute the required content (information) for generating descriptions of geographically located events. Our evaluation shows that our approach extracts information similar to human experts.

Original languageEnglish
Title of host publicationApplications and Innovations in Intelligent Systems XV
Subtitle of host publicationProceedings of AI-2007, the Twenty-seventh SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence
EditorsRichard Ellis, Tony Allen, Miltos Petridis
Place of PublicationGodalming
PublisherSpringer-Verlag
Number of pages14
ISBN (Print)978-1-84800-085-8
Publication statusPublished - 2008

Cite this

Turner, R., Sripada, G. S., Reiter, E. B., & Davy, I. P. (2008). Selecting the content of textual descriptions of geographically located events in spatio-temporal weather data. In R. Ellis, T. Allen, & M. Petridis (Eds.), Applications and Innovations in Intelligent Systems XV: Proceedings of AI-2007, the Twenty-seventh SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence Godalming: Springer-Verlag.

Selecting the content of textual descriptions of geographically located events in spatio-temporal weather data. / Turner, Ross; Sripada, Gowri Somayajulu; Reiter, Ehud Baruch; Davy, Ian P.

Applications and Innovations in Intelligent Systems XV: Proceedings of AI-2007, the Twenty-seventh SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence. ed. / Richard Ellis; Tony Allen; Miltos Petridis. Godalming : Springer-Verlag, 2008.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Turner, R, Sripada, GS, Reiter, EB & Davy, IP 2008, Selecting the content of textual descriptions of geographically located events in spatio-temporal weather data. in R Ellis, T Allen & M Petridis (eds), Applications and Innovations in Intelligent Systems XV: Proceedings of AI-2007, the Twenty-seventh SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence. Springer-Verlag, Godalming.
Turner R, Sripada GS, Reiter EB, Davy IP. Selecting the content of textual descriptions of geographically located events in spatio-temporal weather data. In Ellis R, Allen T, Petridis M, editors, Applications and Innovations in Intelligent Systems XV: Proceedings of AI-2007, the Twenty-seventh SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence. Godalming: Springer-Verlag. 2008
Turner, Ross ; Sripada, Gowri Somayajulu ; Reiter, Ehud Baruch ; Davy, Ian P. / Selecting the content of textual descriptions of geographically located events in spatio-temporal weather data. Applications and Innovations in Intelligent Systems XV: Proceedings of AI-2007, the Twenty-seventh SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence. editor / Richard Ellis ; Tony Allen ; Miltos Petridis. Godalming : Springer-Verlag, 2008.
@inproceedings{b14c16ce855d4125b1ee53e5aca0b735,
title = "Selecting the content of textual descriptions of geographically located events in spatio-temporal weather data",
abstract = "In several domains spatio-temporal data consisting of references to both space and time are collected in large volumes. Textual summaries of spatio-temporal data will complement the map displays used in Geographical Information Systems (CIS) to present data to decision makers. In the RoadSafe project we are working on developing Natural Language Generation (NLG) techniques to generate textual summaries of spatio-temporal numerical weather prediction data. Our approach exploits existing video processing techniques to analyse spatio-temporal weather prediction data and uses Qualitative Spatial Reasoning(QSR) techniques to reason with geographical data in order to compute the required content (information) for generating descriptions of geographically located events. Our evaluation shows that our approach extracts information similar to human experts.",
author = "Ross Turner and Sripada, {Gowri Somayajulu} and Reiter, {Ehud Baruch} and Davy, {Ian P.}",
year = "2008",
language = "English",
isbn = "978-1-84800-085-8",
editor = "Ellis, {Richard } and Allen, {Tony } and Miltos Petridis",
booktitle = "Applications and Innovations in Intelligent Systems XV",
publisher = "Springer-Verlag",

}

TY - GEN

T1 - Selecting the content of textual descriptions of geographically located events in spatio-temporal weather data

AU - Turner, Ross

AU - Sripada, Gowri Somayajulu

AU - Reiter, Ehud Baruch

AU - Davy, Ian P.

PY - 2008

Y1 - 2008

N2 - In several domains spatio-temporal data consisting of references to both space and time are collected in large volumes. Textual summaries of spatio-temporal data will complement the map displays used in Geographical Information Systems (CIS) to present data to decision makers. In the RoadSafe project we are working on developing Natural Language Generation (NLG) techniques to generate textual summaries of spatio-temporal numerical weather prediction data. Our approach exploits existing video processing techniques to analyse spatio-temporal weather prediction data and uses Qualitative Spatial Reasoning(QSR) techniques to reason with geographical data in order to compute the required content (information) for generating descriptions of geographically located events. Our evaluation shows that our approach extracts information similar to human experts.

AB - In several domains spatio-temporal data consisting of references to both space and time are collected in large volumes. Textual summaries of spatio-temporal data will complement the map displays used in Geographical Information Systems (CIS) to present data to decision makers. In the RoadSafe project we are working on developing Natural Language Generation (NLG) techniques to generate textual summaries of spatio-temporal numerical weather prediction data. Our approach exploits existing video processing techniques to analyse spatio-temporal weather prediction data and uses Qualitative Spatial Reasoning(QSR) techniques to reason with geographical data in order to compute the required content (information) for generating descriptions of geographically located events. Our evaluation shows that our approach extracts information similar to human experts.

M3 - Conference contribution

SN - 978-1-84800-085-8

BT - Applications and Innovations in Intelligent Systems XV

A2 - Ellis, Richard

A2 - Allen, Tony

A2 - Petridis, Miltos

PB - Springer-Verlag

CY - Godalming

ER -