DocumentCode
3633453
Title
Constructing Event Templates from Written News
Author
Mitja Trampus;Dunja Mladenic
Volume
3
fYear
2009
Firstpage
507
Lastpage
510
Abstract
We propose a pipeline for learning event templates from a large corpus of textual news articles. An event template is a machine-usable semantic data structure, in our case a graph, describing a certain event type. Most earthquake news reports, for example, semantically fit the template "x people dead, town y shook, at time z". Such templates can be used as an input for information extraction tasks or automated ontology extension. We also present preliminary results in the form of sample extracted templates from Google News articles.
Keywords
"Data mining","Intelligent agent","Pipelines","Ontologies","Conferences","Learning systems","Data structures","Earthquakes","Cities and towns","Statistics"
Publisher
ieee
Conference_Titel
Web Intelligence and Intelligent Agent Technologies, 2009. WI-IAT ´09. IEEE/WIC/ACM International Joint Conferences on
Print_ISBN
978-0-7695-3801-3
Type
conf
DOI
10.1109/WI-IAT.2009.336
Filename
5285036
Link To Document