Elaborating a Knowledge Base for Deep Lexical Semantics.

We describe the methodology for constructing axioms defining event-related words, anchored in core theories of change of state and causality. We first derive from WordNet senses a smaller set of abstract, general "supersenses". We encode axioms for these, and we test them on textual entailment pairs. We look at two specific examples in detail to illustrate both the power of the method and the holes in the knowledge base that it exposes. Then we address the problem of holes more systematically, asking, for example, what kinds of "pairwise interactions" are possible for core theory predicates like change and cause.