Automatic Event and Relation Detection with Seeds of Varying Complexity

Contents

In this paper, we present an approach for automatically detecting events in natural language texts by learning patterns that signal the mentioning of such events. We construe the relevant event types as relations and start with a set of seeds consisting of representative event instances that happen to be known and also to be mentioned frequently in easily available training data. Methods have been developed for the automatic identification of event extents and event triggers. We have learned patterns for a particular domain, i.e., prize award events. Currently we are systematically investigating the criteria for selecting the most effective patterns for the detection of events in sentences and paragraphs. Although the systematic investigation is still under way, we can already report on first very promising results of the method for learning of patterns and for using these patterns in event detection.