Focused entailment graphs for open IE propositions

Omer Levy; Ido Dagan; Jacob Goldberger

doi:10.3115/v1/w14-1610

Focused entailment graphs for open IE propositions

Omer Levy, Ido Dagan, Jacob Goldberger

Bar-Ilan University

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

28 Scopus citations

Abstract

Open IE methods extract structured propositions from text. However, these propositions are neither consolidated nor generalized, and querying them may lead to insufficient or redundant information. This work suggests an approach to organize open IE propositions using entailment graphs. The entailment relation unifies equivalent propositions and induces a specific-to-general structure. We create a large dataset of gold-standard proposition entailment graphs, and provide a novel algorithm for automatically constructing them. Our analysis shows that predicate entailment is extremely context-sensitive, and that current lexical-semantic resources do not capture many of the lexical inferences induced by proposition entailment.

Original language	English
Title of host publication	CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings
Publisher	Association for Computational Linguistics (ACL)
Pages	87-97
Number of pages	11
ISBN (Electronic)	9781941643020
DOIs	https://doi.org/10.3115/v1/w14-1610
State	Published - 2014
Event	18th Conference on Computational Natural Language Learning, CoNLL 2014 - Baltimore, United States Duration: 26 Jun 2014 → 27 Jun 2014

Publication series

Name	CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings

Conference

Conference	18th Conference on Computational Natural Language Learning, CoNLL 2014
Country/Territory	United States
City	Baltimore
Period	26/06/14 → 27/06/14

Bibliographical note

Publisher Copyright:
© 2014 Association for Computational Linguistics.

Funding

This work has been supported by the Israeli Ministry of Science and Technology grant 3-8705, the Israel Science Foundation grant 880/12, and the European Communitys Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 287923 (EXCITEMENT). We would like to thank our reviewers for their insightful comments. This work has been supported by the Israeli Ministry of Science and Technology grant 3-8705, the Israel Science Foundation grant 880/12, and the European Communitys Seventh Framework Programme (FP7/20072013) under grant agreement no. 287923 (EXCITEMENT). We would like to thank our reviewers for their insightful comments.

Funders	Funder number
FP7/2007
Israeli ministry of science and technology	3-8705
Israel Science Foundation	880/12
Seventh Framework Programme	287923, FP7/20072013
Ministry of science and technology, Israel

Access to Document

10.3115/v1/w14-1610

Cite this

Levy, O., Dagan, I., & Goldberger, J. (2014). Focused entailment graphs for open IE propositions. In CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings (pp. 87-97). (CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/w14-1610

@inproceedings{c6d96480b69743519c00af02b51514c5,

title = "Focused entailment graphs for open IE propositions",

abstract = "Open IE methods extract structured propositions from text. However, these propositions are neither consolidated nor generalized, and querying them may lead to insufficient or redundant information. This work suggests an approach to organize open IE propositions using entailment graphs. The entailment relation unifies equivalent propositions and induces a specific-to-general structure. We create a large dataset of gold-standard proposition entailment graphs, and provide a novel algorithm for automatically constructing them. Our analysis shows that predicate entailment is extremely context-sensitive, and that current lexical-semantic resources do not capture many of the lexical inferences induced by proposition entailment.",

author = "Omer Levy and Ido Dagan and Jacob Goldberger",

note = "Publisher Copyright: {\textcopyright} 2014 Association for Computational Linguistics.; 18th Conference on Computational Natural Language Learning, CoNLL 2014 ; Conference date: 26-06-2014 Through 27-06-2014",

year = "2014",

doi = "10.3115/v1/w14-1610",

language = "אנגלית",

series = "CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings",

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

pages = "87--97",

booktitle = "CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings",

address = "ארצות הברית",

}

Levy, O, Dagan, I & Goldberger, J 2014, Focused entailment graphs for open IE propositions. in CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings. CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings, Association for Computational Linguistics (ACL), pp. 87-97, 18th Conference on Computational Natural Language Learning, CoNLL 2014, Baltimore, United States, 26/06/14. https://doi.org/10.3115/v1/w14-1610

Focused entailment graphs for open IE propositions. / Levy, Omer; Dagan, Ido ; Goldberger, Jacob.
CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL), 2014. p. 87-97 (CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings).

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

TY - GEN

T1 - Focused entailment graphs for open IE propositions

AU - Levy, Omer

AU - Dagan, Ido

AU - Goldberger, Jacob

PY - 2014

Y1 - 2014

N2 - Open IE methods extract structured propositions from text. However, these propositions are neither consolidated nor generalized, and querying them may lead to insufficient or redundant information. This work suggests an approach to organize open IE propositions using entailment graphs. The entailment relation unifies equivalent propositions and induces a specific-to-general structure. We create a large dataset of gold-standard proposition entailment graphs, and provide a novel algorithm for automatically constructing them. Our analysis shows that predicate entailment is extremely context-sensitive, and that current lexical-semantic resources do not capture many of the lexical inferences induced by proposition entailment.

AB - Open IE methods extract structured propositions from text. However, these propositions are neither consolidated nor generalized, and querying them may lead to insufficient or redundant information. This work suggests an approach to organize open IE propositions using entailment graphs. The entailment relation unifies equivalent propositions and induces a specific-to-general structure. We create a large dataset of gold-standard proposition entailment graphs, and provide a novel algorithm for automatically constructing them. Our analysis shows that predicate entailment is extremely context-sensitive, and that current lexical-semantic resources do not capture many of the lexical inferences induced by proposition entailment.

UR - https://www.scopus.com/pages/publications/84959927632

U2 - 10.3115/v1/w14-1610

DO - 10.3115/v1/w14-1610

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

AN - SCOPUS:84959927632

T3 - CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings

SP - 87

EP - 97

BT - CoNLL 2014 - 18th Conference on Computational Natural Language Learning, Proceedings

PB - Association for Computational Linguistics (ACL)

T2 - 18th Conference on Computational Natural Language Learning, CoNLL 2014

Y2 - 26 June 2014 through 27 June 2014

ER -

Focused entailment graphs for open IE propositions

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this