Commonsense knowledge acquisition and applications

Computers are increasingly expected to make smart decisions based on what humans consider commonsense. This would require computers to understand their environment, including properties of objects in the environment (e.g., a wheel is round), relations between objects (e.g., two wheels are part of a bike, or a bike is slower than a car) and interactions of objects (e.g., a driver drives a car on the road). The goal of this dissertation is to investigate automated methods for acquisition of large-scale, semantically organized commonsense knowledge. This goal poses challenges because commonsense knowledge is: (i) implicit and sparse as humans do not explicitly express the obvious, (ii) multimodal as it is spread across textual and visual contents, (iii) affected by reporting bias as uncommon facts are reported disproportionally, (iv) context dependent and thus holds merely with a certain confidence. Prior state-of-the-art methods to acquire commonsense are either not automated or based on shallow representations. Thus, they cannot produce large-scale, semantically organized commonsense knowledge. To achieve the goal, we divide the problem space into three research directions, making up the core contributions of this dissertation: • Properties of objects: acquisition of properties like hasSize, hasShape, etc. We develop WebChild, a semi-supervised method to compile semantically organized properties. • Relationships between objects: acquisition of relations like largerThan, partOf, memberOf, etc. We develop CMPKB, a linear-programming based method to compile comparative relations, and, we develop PWKB, a method based on statistical and logical inference to compile part-whole relations. • Interactions between objects: acquisition of activities like drive a car, park a car, etc., with attributes such as temporal or spatial attributes. We develop Knowlywood, a method based on semantic parsing and probabilistic graphical models to compile activity knowledge. Together, these methods result in the construction of a large, clean and semantically organized Commonsense Knowledge Base that we call WebChild KB.