Identifying Underlying Commonsense Knowledge in Definitions

We present a framework that learns commonsense temporal knowledge from word definitions. Our work differs from existing systems in both the way definitions are axiomatized and the way knowledge is inferred from those axioms. First, we go beyond axiomatizing just the literal interpretation of a definition by considering the underlying subtext and assumptions a reader has to make to understand a definition. Secondly, we cluster the concept axioms into small event theories that we use to predict the co-occurrence of concepts in simple scenarios. These predictions allow us to identify knowledge derived from the complex interactions among several definitions that would otherwise be ignored. We show that this framework can derive temporal knowledge across several different concept domains. Results are compared to human judgment and demonstrate the effect several features have on evaluation scores.