Acquiring Applicable Common Sense Knowledge from the Web

Abstract

In this paper, a framework for acquiring common sense knowledge from the Web is presented. Common sense knowledge includes information about the world that humans use in their everyday lives. To acquire this knowledge, relationships between nouns are retrieved by using search phrases with automatically filled constituents. Through empirical analysis of the acquired nouns over WordNet, probabilities are produced for relationships between a concept and a word rather than between two words. A specific goal of our acquisition method is to acquire knowledge that can be successfully applied to NLP problems. We test the validity of the acquired knowledge by means of an application to the problem of word sense disambiguation. Results show that the knowledge can be used to improve the accuracy of a state of the art unsupervised disambiguation system.