Mining situations and actions from news
| Authors | |
|---|---|
| Year of publication | 2006 |
| Type | Article in Proceedings |
| Conference | Znalosti 2006 |
| MU Faculty or unit | |
| Citation | |
| 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: |