Representing Verbs as Argument Concepts
Computation and Language
2018-04-04 v1 Artificial Intelligence
Abstract
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.
Cite
@article{arxiv.1803.00729,
title = {Representing Verbs as Argument Concepts},
author = {Yu Gong and Kaiqi Zhao and Kenny Q. Zhu},
journal= {arXiv preprint arXiv:1803.00729},
year = {2018}
}
Comments
7 pages, 2 figures, AAAI 2016