In the new paper Does BERT Solve Commonsense Task via Commonsense Knowledge?, a team of researchers from Westlake University, Fudan University and Microsoft Research Asia dive deep into the large language model to discover how it encodes the structured commonsense knowledge it leverages on downstream commonsense tasks. The proven successes of pretrained language models such as BERT on various downstream tasks has stimulated research investigating the linguistic knowledge inside the model. Previous studies have revealed shallow syntactic, semantic and word sense knowledge in BERT, however, the question of how BERT deals with commonsense tasks has been relatively unexamined. CommonsenseQA is a multiple-choice question answering dataset built upon the CONCEPTNET knowledge graph. The researchers extracted multiple target concepts with the same semantic relation to a single source concept from CONCEPTNET, where each question has one of three target concepts as the correct answer. For example, "bird" is the source concept in the question "Where does a wild bird usually live?" and "countryside" is the correct answer from the possible target concepts "cage," "windowsill," and "countryside."
The central challenge in commonsense knowledge representation research is to develop content theories that achieve a high degree of both competency and coverage. We describe a new methodology for constructing formal theories in commonsense knowledge domains that complements traditional knowledge representation approaches by first addressing issues of coverage. These concepts are sorted into a manageable number of coherent domains, one of which is the representational area of commonsense human memory. These representational areas are then analyzed using more traditional knowledge representation techniques, as demonstrated in this article by our treatment of commonsense human memory.
Understanding commonsense reasoning is one of the core challenges of AI. We are exploring an approach inspired by cognitive science, called analogical chaining, to create cognitive systems that can perform commonsense reasoning. Just as rules are chained in deductive systems, multiple analogies build upon each other’s inferences in analogical chaining. The cases used in analogical chaining – called common sense units – are small, to provide inferential focus and broader transfer. Importantly, such common sense units can be learned via natural language instruction, thereby increasing the ease of extending such systems. This paper describes analogical chaining, natural language instruction via microstories, and some subtleties that arise in controlling reasoning. The utility of this technique is demonstrated by performance of an implemented system on problems from the Choice of Plausible Alternatives test of commonsense causal reasoning.
The purpose of this paper is twofold: (i) we argue that the structure of commonsense knowledge must be discovered, rather than invented; and (ii) we argue that natural language, which is the best known theory of our (shared) commonsense knowledge, should itself be used as a guide to discovering the structure of commonsense knowledge. In addition to suggesting a systematic method to the discovery of the structure of commonsense knowledge, the method we propose seems to also provide an explanation for a number of phenomena in natural language, such as metaphor, intensionality, and the semantics of nominal compounds. Admittedly, our ultimate goal is quite ambitious, and it is no less than the systematic 'discovery' of a well-typed ontology of commonsense knowledge, and the subsequent formulation of the long-awaited goal of a meaning algebra.
A full book, available for free in PDF form.From the preface:A major problem in artificial intelligence is to endow computers with commonsense knowledge of the world and with the ability to use that knowledge sensibly. A large body of research has studied this problem through careful analysis of typical examples of reasoning in a variety of commonsense domains. The immediate aim of this research is to develop a rich language for expressing commonsense knowledge, and inference techniques for carrying out commonsense reasoning. This book provides an introduction and a survey of this body of research. It is, to the best of my knowledge, the first book to attempt this.The book is designed to be used as a textbook for a one-semester graduate course on knowledge representation.Morgan Kaufmann