Commonsense Knowledge in Word Associations and ConceptNet

Humans use countless basic, shared facts about the world to efficiently navigate in their environment. This commonsense knowledge is rarely communicated explicitly, however, understanding how commonsense knowledge is represented in different paradigms is important for both deeper understanding of hu...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Liu, Chunhua, Cohn, Trevor, Frermann, Lea
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 20.09.2021
Subjects
Cognition
Computer Science - Computation and Language
Crowdsourcing
Graphs
Knowledge
Knowledge representation
Reasoning
Relational data bases
Online AccessGet full text

Cover

More Information
Summary:Humans use countless basic, shared facts about the world to efficiently navigate in their environment. This commonsense knowledge is rarely communicated explicitly, however, understanding how commonsense knowledge is represented in different paradigms is important for both deeper understanding of human cognition and for augmenting automatic reasoning systems. This paper presents an in-depth comparison of two large-scale resources of general knowledge: ConcpetNet, an engineered relational database, and SWOW a knowledge graph derived from crowd-sourced word associations. We examine the structure, overlap and differences between the two graphs, as well as the extent to which they encode situational commonsense knowledge. We finally show empirically that both resources improve downstream task performance on commonsense reasoning benchmarks over text-only baselines, suggesting that large-scale word association data, which have been obtained for several languages through crowd-sourcing, can be a valuable complement to curated knowledge graphs
ISSN:2331-8422
DOI:10.48550/arxiv.2109.09309