The Winograd Schema Challenge and Reasoning about Correlation

Dan Bailey, University of Nebraska at Omaha
Amelia Harrison, University of Texas at Austin
Yuliya Lierler, University of Nebraska at Omaha
Vladimir Lifschitz, University of Texas at Austin
Julian Michael, University of Texas at Austin

Abstract

The Winograd Schema Challenge is an alternative to the Turing Test that may provide a more meaningful measure of machine intelligence. It poses a set of coreference resolution problems that cannot be solved without human-like reasoning. In this paper, we take the view that the solution to such problems lies in establishing discourse coherence. Specifically, we examine two types of rhetorical relations that can be used to establish discourse coherence: positive and negative correlation. We introduce a framework for reasoning about correlation between sentences, and show how this framework can be used to justify solutions to some Winograd Schema problems.