Using Answer Set Programming for Commonsense Reasoning in the Winograd Schema Challenge
This work addresses natural language understanding for AI systems, but it is incremental as it builds on existing ASP methods for a specific benchmark.
The authors tackled the Winograd Schema Challenge (WSC) by using Answer Set Programming (ASP) with graph-subgraph isomorphism to incorporate commonsense knowledge, achieving a result of solving 240 out of 291 problems.
The Winograd Schema Challenge (WSC) is a natural language understanding task proposed as an alternative to the Turing test in 2011. In this work we attempt to solve WSC problems by reasoning with additional knowledge. By using an approach built on top of graph-subgraph isomorphism encoded using Answer Set Programming (ASP) we were able to handle 240 out of 291 WSC problems. The ASP encoding allows us to add additional constraints in an elaboration tolerant manner. In the process we present a graph based representation of WSC problems as well as relevant commonsense knowledge. This paper is under consideration for acceptance in TPLP.