Human-Centric AI with Common Sense

This book enables readers tounderstand thechallenges and opportunities ofdeveloping human-centered AI withcommonsense reasoning abilities. Despite apparent accuracy improvements brought bylarge neural models across task benchmarks, common sense is still lacking. The lack ofcommon sense affects many tasks, including story understanding, decision-making, and question answering. Commonsense knowledge and reasoning have long been considered the"black matter" ofAI, raising concerns about thetrustworthiness and applicability ofAI methods in both autonomous and hybrid applications. This book describes how to design a more robust, collaborative, explainable, and responsible AI through incorporating neuro-symbolic commonsense reasoning. In addition, thebook provides examples ofhow these properties ofAI can facilitate a wide range ofsocial-good applications in digital democracy, traffic monitoring, education, and robotics. What makes commonsense reasoning such a unique and impactful challenge? What can we learn fromcognitive research when designing and developing AI systems? How can we approach building responsible, robust, collaborative, and explainable AI withcommon sense? And finally, what is theimpact ofthis work onhuman-AI teaming? This book provides an accessible introduction and exploration ofthese topics.