Representing Verbs as Argument Concepts
This addresses the challenge of verb understanding in natural language processing, which is incremental as it builds on existing semantic representation methods.
The paper tackles the problem of abstracting verb arguments into a set of noun concepts, called 'argument concepts', to represent fine-grained semantics, and presents a framework that achieves high accuracy in automatically inferring these concepts.
Verbs play an important role in the understanding of natural language text. This paper studies the problem of abstracting the subject and object arguments of a verb into a set of noun concepts, known as the "argument concepts". This set of concepts, whose size is parameterized, represents the fine-grained semantics of a verb. For example, the object of "enjoy" can be abstracted into time, hobby and event, etc. We present a novel framework to automatically infer human readable and machine computable action concepts with high accuracy.