TY - GEN
T1 - Commonsense knowledge extraction using concepts properties
AU - Blanco, Eduardo
AU - Cankaya, Hakki C.
AU - Moldovan, Dan
PY - 2011
Y1 - 2011
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=80052421892&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80052421892&partnerID=8YFLogxK
M3 - Conference contribution
SN - 9781577355014
T3 - Proceedings of the 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24
SP - 222
EP - 227
BT - Proceedings of the 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24
T2 - 24th International Florida Artificial Intelligence Research Society, FLAIRS - 24
Y2 - 18 May 2011 through 20 May 2011
ER -