Event Recognition on News Stories and Semi-Automatic Population of an Ontology

This paper describes a system which recognizes events on news stories. Our system classifies stories and populates a hand-crafted ontology with new instances of classes defined in it. Currently, our system recognizes events which can be classified as belonging to a single category and it also recognizes overlapping events within one article (more than one event is recognized). In each case, the system provides a confidence value associated to the suggested classification. Our system uses Information Extraction and Machine Learning technologies. The system was tested using a corpus of 200 news articles from an archive of electronic news stories describing the academic life of the Knowledge Media (KMi). In particular, these news stories describe events such as a project award, publications, visits, etc.