Cross-document temporal and spatial person tracking system demonstration

Heng Ji, Zheng Chen

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

Abstract

Traditional Information Extraction (IE) systems identify many unconnected facts. The objective of this paper is to define a new cross-document information extraction task and demonstrate a system which can extract, rank and track events in two dimensions: temporal and spatial. The system can automatically label the person entities involved in significant events as 'centroid arguments', and then present the events involving the same centroid on a time line and on a geographical map.

Original languageEnglish (US)
Title of host publicationNAACL-HLT 2009 - Human Language Technologies
Subtitle of host publication2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Demonstration Session
EditorsMichael Johnston, Fred Popowich
PublisherAssociation for Computational Linguistics (ACL)
Pages1-4
Number of pages4
ISBN (Electronic)9781932432428
StatePublished - 2009
Externally publishedYes
Event2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2009 - Boulder, United States
Duration: Jun 1 2009Jun 3 2009

Publication series

NameNAACL-HLT 2009 - Human Language Technologies: 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Demonstration Session

Conference

Conference2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2009
Country/TerritoryUnited States
CityBoulder
Period6/1/096/3/09

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Cross-document temporal and spatial person tracking system demonstration'. Together they form a unique fingerprint.

Cite this