Representing Verbs as Argument Concepts

03/02/2018
by   Yu Gong, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/30/2022

Large-scale Multi-granular Concept Extraction Based on Machine Reading Comprehension

The concepts in knowledge graphs (KGs) enable machines to understand nat...
research
11/03/2022

Open-Vocabulary Argument Role Prediction for Event Extraction

The argument role in event extraction refers to the relation between an ...
research
05/26/2020

Refining Implicit Argument Annotation For UCCA

Few resources represent implicit roles for natural language understandin...
research
10/07/2020

Exploring the Role of Argument Structure in Online Debate Persuasion

Online debate forums provide users a platform to express their opinions ...
research
10/13/2020

"What Are You Trying to Do?" Semantic Typing of Event Processes

This paper studies a new cognitively motivated semantic typing task, mul...
research
03/07/2023

ELODIN: Naming Concepts in Embedding Spaces

Despite recent advancements, the field of text-to-image synthesis still ...
research
08/30/2023

A Dataflow Analysis for Comparing and Reordering Predicate Arguments

In this work, which is done in the context of a (moded) logic programmin...

Please sign up or login with your details

Forgot password? Click here to reset