Blending NLP and Machine Learning for the Development of Winograd Schemas

The Winograd Schema Challenge (WSC), a novel litmus test for machine intelligence, has been proposed to advance the field of AI. Over the last decade, AI researchers have become increasingly interested in this challenge. While a common and trivial task for humans, studies have shown that the WSC is still difficult for current AI systems. Tackling the challenge would likely require
access to a sufficiently rich set of Winograd schema examples, which are currently limited in their number and too cumbersome to create completely manually. Towards addressing these limitations, we propose a machine-driven approach for the development of large numbers of schemas. Our empirical evaluation suggests that our developed system, which blends the advantages of Machine
Learning and Natural Language Processing, is able to automatically develop Winograd schemas autonomously, or considerably help humans in the development task.