Event Recognition using Information Extraction Techniques

This paper describes a system which recognizes events on stories. Our system classifies stories and populates a KMi Planet ontology with new instances of classes defined in it. Currently, the system recognizes events which can be classified as belonging to a single category and it also recognizes overlapping events (more than one event is recognized in the story). In each case, the system provides a confidence value associated to the suggested classification. In our event recognition system we use Information Extraction and Machine Learning technologies. We have tested this system using an archive of stories describing the academic life of our institution (these stories describe events such as an project award, publications, visits, etc.)