Using Textual Patterns to Learn Expected Event Frequencies

Jonathan Gordon, Lenhart K. Schubert

Abstract: Commonsense reasoning requires knowledge about the frequency with which ordinary events and activities occur: How often do people eat a sandwich, go to sleep, write a book, or get married? This paper introduces work to acquire a knowledge base pairing factoids about such events with frequency categories learned from simple textual patterns. We are releasing a collection of the resulting event frequencies, which are evaluated for accuracy, and we demonstrate an initial application of the results to the problem of knowledge refinement.