PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Learning event templates on news articles
Mitja Trampus and Dunja Mladenić
In: SIKDD 2009, 12-16 Okt 2009, Ljubljana, Slovenia.

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. For instance, most earthquake news reports mention something in direction of "x people dead” or “town y shook at time z". Such templates can be used as an input for information extraction tasks or automated ontology extension. We present preliminary results of applying the proposed pipeline on a subset of News articles.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Computational, Information-Theoretic Learning with Statistics
Information Retrieval & Textual Information Access
ID Code:6434
Deposited By:Jan Rupnik
Deposited On:08 March 2010