TY - GEN
T1 - Learning entailment rules for unary templates
AU - Szpektor, Idan
AU - Dagan, Ido
PY - 2008
Y1 - 2008
N2 - Most work on unsupervised entailment rule acquisition focused on rules between templates with two variables, ignoring unary rules - entailment rules between templates with a single variable. In this paper we investigate two approaches for unsupervised learning of such rules and compare the proposed methods with a binary rule learning method. The results show that the learned unary rule-sets outperform the binary rule-set. In addition, a novel directional similarity measure for learning entailment, termed Balanced-Inclusion, is the best performing measure.
AB - Most work on unsupervised entailment rule acquisition focused on rules between templates with two variables, ignoring unary rules - entailment rules between templates with a single variable. In this paper we investigate two approaches for unsupervised learning of such rules and compare the proposed methods with a binary rule learning method. The results show that the learned unary rule-sets outperform the binary rule-set. In addition, a novel directional similarity measure for learning entailment, termed Balanced-Inclusion, is the best performing measure.
UR - http://www.scopus.com/inward/record.url?scp=70449695892&partnerID=8YFLogxK
U2 - 10.3115/1599081.1599188
DO - 10.3115/1599081.1599188
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:70449695892
SN - 9781905593446
T3 - Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference
SP - 849
EP - 856
BT - Coling 2008 - 22nd International Conference on Computational Linguistics, Proceedings of the Conference
PB - Association for Computational Linguistics (ACL)
T2 - 22nd International Conference on Computational Linguistics, Coling 2008
Y2 - 18 August 2008 through 22 August 2008
ER -