TY - GEN
T1 - Learning to Predict Denotational Probabilities For Modeling Entailment
AU - Lai, Alice
AU - Hockenmaier, Julia
N1 - Funding Information:
This work was supported by NSF Grants 1563727, 1405883, and 1053856, and by a Google Research Award.
Publisher Copyright:
© 2017 Association for Computational Linguistics.
PY - 2017
Y1 - 2017
N2 - We propose a framework that captures the denotational probabilities of words and phrases by embedding them in a vector space, and present a method to induce such an embedding from a dataset of denotational probabilities. We show that our model successfully predicts denotational probabilities for unseen phrases, and that its predictions are useful for textual entailment datasets such as SICK and SNLI.
AB - We propose a framework that captures the denotational probabilities of words and phrases by embedding them in a vector space, and present a method to induce such an embedding from a dataset of denotational probabilities. We show that our model successfully predicts denotational probabilities for unseen phrases, and that its predictions are useful for textual entailment datasets such as SICK and SNLI.
UR - http://www.scopus.com/inward/record.url?scp=85021675712&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85021675712&partnerID=8YFLogxK
U2 - 10.18653/v1/e17-1068
DO - 10.18653/v1/e17-1068
M3 - Conference contribution
AN - SCOPUS:85021675712
T3 - 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference
SP - 721
EP - 730
BT - Long Papers - Continued
PB - Association for Computational Linguistics (ACL)
T2 - 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017
Y2 - 3 April 2017 through 7 April 2017
ER -