Commonsense knowledge extraction using concepts properties

Eduardo Blanco, Hakki C. Cankaya, Dan Moldovan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

This paper presents a semantically grounded method for extracting commonsense knowledge. First, commonsense rules are identified, e.g., one cannot see imaginary objects. Second, those rules are combined with a basic semantic representation in order to infer commonsense knowledge facts, e.g. one cannot see a flying carpet. Further combinations of semantic relations with inferred commonsense facts are proposed and analyzed. Results show that this novel method is able to extract thousands of commonsense facts with little human interaction and high accuracy.

Original languageEnglish (US)
Title of host publicationProceedings of the 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24
Pages222-227
Number of pages6
StatePublished - 2011
Externally publishedYes
Event24th International Florida Artificial Intelligence Research Society, FLAIRS - 24 - Palm Beach, FL, United States
Duration: May 18 2011May 20 2011

Publication series

NameProceedings of the 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24

Other

Other24th International Florida Artificial Intelligence Research Society, FLAIRS - 24
Country/TerritoryUnited States
CityPalm Beach, FL
Period5/18/115/20/11

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Commonsense knowledge extraction using concepts properties'. Together they form a unique fingerprint.

Cite this