Global learning of focused entailment graphs

Jonathan Berant; Ido Dagan; Jacob Goldberger

Global learning of focused entailment graphs

Jonathan Berant
, Ido Dagan
, Jacob Goldberger

Tel Aviv University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Scopus citations

Abstract

We propose a global algorithm for learning entailment relations between predicates. We define a graph structure over predicates that represents entailment relations as directed edges, and use a global transitivity constraint on the graph to learn the optimal set of edges, by formulating the optimization problem as an Integer Linear Program. We motivate this graph with an application that provides a hierarchical summary for a set of propositions that focus on a target concept, and show that our global algorithm improves performance by more than 10% over baseline algorithms.

Original language	English
Title of host publication	ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings
Editors	Jan Hajic, Sandra Carberry, Stephen Clark
Publisher	Association for Computational Linguistics (ACL)
Pages	1220-1229
Number of pages	10
ISBN (Electronic)	1932432663, 9781932432664
State	Published - 2010
Event	48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 - Uppsala, Sweden Duration: 11 Jul 2010 → 16 Jul 2010

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
Volume	2010-July
ISSN (Print)	0736-587X

Conference

Conference	48th Annual Meeting of the Association for Computational Linguistics, ACL 2010
Country/Territory	Sweden
City	Uppsala
Period	11/07/10 → 16/07/10

Bibliographical note

Publisher Copyright:
© 2010 Association for Computational Linguistics.

Funding

We would like to thank Roy Bar-Haim, David Carmel and the anonymous reviewers for their useful comments. We also thank Dafna Berant and the nine students who prepared the gold standard data set. This work was developed under the collaboration of FBK-irst/University of Haifa and was partially supported by the Israel Science Foundation grant 1112/08. The first author is grateful to the Azrieli Foundation for the award of an Azrieli Fellowship, and has carried out this research in partial fulllment of the requirements for the Ph.D. degree.

Funders	Funder number
Israel Science Foundation	1112/08
Azrieli Foundation

Cite this

Berant, J., Dagan, I., & Goldberger, J. (2010). Global learning of focused entailment graphs. In J. Hajic, S. Carberry, & S. Clark (Eds.), ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings (pp. 1220-1229). (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 2010-July). Association for Computational Linguistics (ACL).

Berant, Jonathan ; Dagan, Ido ; Goldberger, Jacob. / Global learning of focused entailment graphs. ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings. editor / Jan Hajic ; Sandra Carberry ; Stephen Clark. Association for Computational Linguistics (ACL), 2010. pp. 1220-1229 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{20e1fd81b5fa4d92af0e7c703180ba3d,

title = "Global learning of focused entailment graphs",

abstract = "We propose a global algorithm for learning entailment relations between predicates. We define a graph structure over predicates that represents entailment relations as directed edges, and use a global transitivity constraint on the graph to learn the optimal set of edges, by formulating the optimization problem as an Integer Linear Program. We motivate this graph with an application that provides a hierarchical summary for a set of propositions that focus on a target concept, and show that our global algorithm improves performance by more than 10\% over baseline algorithms.",

author = "Jonathan Berant and Ido Dagan and Jacob Goldberger",

note = "Publisher Copyright: {\textcopyright} 2010 Association for Computational Linguistics.; 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010 ; Conference date: 11-07-2010 Through 16-07-2010",

year = "2010",

language = "אנגלית",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

pages = "1220--1229",

editor = "Jan Hajic and Sandra Carberry and Stephen Clark",

booktitle = "ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings",

address = "ארצות הברית",

}

Berant, J, Dagan, I & Goldberger, J 2010, Global learning of focused entailment graphs. in J Hajic, S Carberry & S Clark (eds), ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings. Proceedings of the Annual Meeting of the Association for Computational Linguistics, vol. 2010-July, Association for Computational Linguistics (ACL), pp. 1220-1229, 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010, Uppsala, Sweden, 11/07/10.

Global learning of focused entailment graphs. / Berant, Jonathan; Dagan, Ido ; Goldberger, Jacob.
ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings. ed. / Jan Hajic; Sandra Carberry; Stephen Clark. Association for Computational Linguistics (ACL), 2010. p. 1220-1229 (Proceedings of the Annual Meeting of the Association for Computational Linguistics; Vol. 2010-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Global learning of focused entailment graphs

AU - Berant, Jonathan

AU - Dagan, Ido

AU - Goldberger, Jacob

PY - 2010

Y1 - 2010

N2 - We propose a global algorithm for learning entailment relations between predicates. We define a graph structure over predicates that represents entailment relations as directed edges, and use a global transitivity constraint on the graph to learn the optimal set of edges, by formulating the optimization problem as an Integer Linear Program. We motivate this graph with an application that provides a hierarchical summary for a set of propositions that focus on a target concept, and show that our global algorithm improves performance by more than 10% over baseline algorithms.

AB - We propose a global algorithm for learning entailment relations between predicates. We define a graph structure over predicates that represents entailment relations as directed edges, and use a global transitivity constraint on the graph to learn the optimal set of edges, by formulating the optimization problem as an Integer Linear Program. We motivate this graph with an application that provides a hierarchical summary for a set of propositions that focus on a target concept, and show that our global algorithm improves performance by more than 10% over baseline algorithms.

UR - https://www.scopus.com/pages/publications/85118420976

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85118420976

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 1220

EP - 1229

BT - ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings

A2 - Hajic, Jan

A2 - Carberry, Sandra

A2 - Clark, Stephen

PB - Association for Computational Linguistics (ACL)

T2 - 48th Annual Meeting of the Association for Computational Linguistics, ACL 2010

Y2 - 11 July 2010 through 16 July 2010

ER -

Berant J, Dagan I , Goldberger J. Global learning of focused entailment graphs. In Hajic J, Carberry S, Clark S, editors, ACL 2010 - 48th Annual Meeting of the Association for Computational Linguistics, Conference Proceedings. Association for Computational Linguistics (ACL). 2010. p. 1220-1229. (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

Global learning of focused entailment graphs

Abstract

Publication series

Conference

Bibliographical note

Funding

Other files and links

Fingerprint

Cite this