Representing Verbs as Argument Concepts

AAAI 2016 pp. 2615-2621

doi:10.1609/AAAI.V30I1.10324 /aaai/2016/gong2016aaai-representing/

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.

PDF AAAI Semantic Scholar

Cite

Text

Gong et al. "Representing Verbs as Argument Concepts." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.10324

Markdown

[Gong et al. "Representing Verbs as Argument Concepts." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/gong2016aaai-representing/) doi:10.1609/AAAI.V30I1.10324

BibTeX

@inproceedings{gong2016aaai-representing,
  title     = {{Representing Verbs as Argument Concepts}},
  author    = {Gong, Yu and Zhao, Kaiqi and Zhu, Kenny Qili},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {2615-2621},
  doi       = {10.1609/AAAI.V30I1.10324},
  url       = {https://mlanthology.org/aaai/2016/gong2016aaai-representing/}
}