Publication details

Mining situations and actions from news



Year of publication 2006
Type Article in Proceedings
Conference Znalosti 2006
MU Faculty or unit

Faculty of Informatics

Field Informatics
Keywords text filtering; information extraction; term extraction
Description The definite goal of this project is building tools for automatic filtering news reports on flood, for extracting information from such reports and the use of this extracted information for finding important terms (single words, name/verb phrases, named entities etc.) and eventually building a domain ontology. In this paper we focus on classifying sentences that describe either a situation or an action by means of machine learning. The results of various learning algorithms are discussed. We also bring first results on term extraction.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info