Using ConceptNet to Teach Common Sense to an Automated Theorem Prover

In recent years, numerous benchmarks for commonsense reasoning have been presented which cover different areas: the Choice of Plausible Alternatives Challenge (COP A) [17] requires causal reasoning in everyday situations, the Winograd Schema Challenge [8] addresses difficult cases of pronoun disambiguation, the TriangleCOP A Challenge [9] focuses on human relationships and emotions, and the Story Cloze Test with the ROCStories Corpora [11] focuses on the ability to determine a plausible ending for a given short story, to name just a few. In our system, we focus on the COP A challenge where each problem consists of a problem description (the premise), a question, and two answer candidates (called alternatives). See Figure 1 for an example. Most approaches tackling these problems are based on machine learning or exploit statistical properties of the natural language input (see e.g.