TY - GEN
T1 - A logic prover approach to predicting textual similarity
AU - Blanco, Eduardo
AU - Moldovan, Dan
PY - 2013
Y1 - 2013
N2 - This paper presents a logic prover approach to predicting textual similarity. Sentences are represented using three logic forms capturing different levels of knowledge, from only content words to semantic representations extracted with an existing semantic parser. A logic prover is used to find proofs and derive semantic features that are combined in a machine learning framework. Experimental results show that incorporating the semantic structure of sentences yields better results than simpler pairwise word similarity measures.
AB - This paper presents a logic prover approach to predicting textual similarity. Sentences are represented using three logic forms capturing different levels of knowledge, from only content words to semantic representations extracted with an existing semantic parser. A logic prover is used to find proofs and derive semantic features that are combined in a machine learning framework. Experimental results show that incorporating the semantic structure of sentences yields better results than simpler pairwise word similarity measures.
UR - http://www.scopus.com/inward/record.url?scp=84889813527&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84889813527&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84889813527
SN - 9781577356059
T3 - FLAIRS 2013 - Proceedings of the 26th International Florida Artificial Intelligence Research Society Conference
SP - 255
EP - 258
BT - FLAIRS 2013 - Proceedings of the 26th International Florida Artificial Intelligence Research Society Conference
T2 - 26th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2013
Y2 - 22 May 2013 through 24 May 2013
ER -