Essential Features in a Theory of Context for Enabling Artificial General Intelligence

Despite recent Artificial Intelligence (AI) advances in narrow task areas such as face recognition and natural language processing, the emergence of general machine intelligence continues to be elusive. Such an AI must overcome several challenges, one of which is the ability to be aware of, and appropriately handle, context. In this article, we argue that context needs to be rigorously treated as a first-class citizen in AI research and discourse for achieving true general machine intelligence. Unfortunately, context is only loosely defined, if at all, within AI research. This article aims to synthesize the myriad pragmatic ways in which context has been used, or implicitly assumed, as a core concept in multiple AI sub-areas, such as representation learning and commonsense reasoning. While not all definitions are equivalent, we systematically identify a set of seven features associated with context in these sub-areas. We argue that such features are necessary for a sufficiently rich theory of context, as applicable to practical domains and applications in AI.

Modeling and Reasoning in Event Calculus using Goal-Directed Constraint Answer Set Programming

Automated commonsense reasoning (CR) is essential for building human-like AI systems featuring, for example, explainable AI. Event calculus (EC) is a family of formalisms that model CR with a sound, logical basis. Previous attempts to mechanize reasoning using EC faced difficulties in the treatment of the continuous change in dense domains (e.g. time and other physical quantities), constraints among variables, default negation, and the uniform application of different inference methods, among others. We propose the use of s(CASP), a query-driven, top-down execution model for Predicate Answer Set Programming with Constraints, to model and reason using EC. We show how EC scenarios can be naturally and directly encoded in s(CASP) and how it enables deductive and abductive reasoning tasks in domains featuring constraints involving both dense time and dense fluents.

WinoGrande

Commonsense reasoning remains a major challenge in AI, and yet, recent progresses on benchmarks may seem to suggest otherwise. In particular, the recent neural language models have reported above 90% accuracy on the Winograd Schema Challenge (WSC), a commonsense benchmark originally designed to be unsolvable for statistical models that rely simply on word associations. This raises an important question---whether these models have truly acquired robust commonsense capabilities or they rely on spurious biases in the dataset that lead to an overestimation of the true capabilities of machine commonsense. To investigate this question, we introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original WSC, but adjusted to improve both the scale and the hardness of the dataset. The key steps of the dataset construction consist of (1) large-scale crowdsourcing, followed by (2) systematic bias reduction using a novel AFLITE algorithm that generalizes human-detectable word associations to machine-detectable embedding associations. Our experiments demonstrate that state-of-the-art models achieve considerably lower accuracy (59.4%-79.1%) on WINOGRANDE compared to humans (94%), confirming that the high performance on the original WSC was inflated by spurious biases in the dataset. Furthermore, we report new state-of-the-art results on five related benchmarks with emphasis on their dual implications. On the one hand, they demonstrate the effectiveness of WINOGRANDE when used as a resource for transfer learning. On the other hand, the high performance on all these benchmarks suggests the extent to which spurious biases are prevalent in all such datasets, which motivates further research on algorithmic bias reduction.

Automated Common-sense Spatial Reasoning: Still a Huge Challenge

Achieving “commonsense reasoning” capabilities has been one of the goals of AI since its inception. However, as Marcus and Davis have recently argued, “Common sense is not just the hardest problem for AI; in the long run, it’s also the most important problem”. Moreover, it is generally accepted that space (and time) underlie much of what we regard as commonsense reasoning. Despite many successes in dealing with particular restricted types of spatial information, the development of a system capable of carrying out automated spatial reasoning of similar diversity to what one finds in ordinary natural language descriptions, seems to be a long way off. The chapter gives a general (though not comprehensive) overview of the goal of automating commonsense spatial reasoning by means of symbolic representations and reasoning. Existing work is surveyed, the nature of the goal clarified, and the problem analysed into seven interacting sub-problems.