Learning to exploit structured resources for lexical inference

Vered Shwartz; Omer Levy; Ido Dagan; Jacob Goldberger

doi:10.18653/v1/k15-1018

Learning to exploit structured resources for lexical inference

Vered Shwartz, Omer Levy, Ido Dagan, Jacob Goldberger

Bar-Ilan University

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

10 Scopus citations

Abstract

Massive knowledge resources, such as Wikidata, can provide valuable information for lexical inference, especially for proper-names. Prior resource-based approaches typically select the subset of each resource’s relations which are relevant for a particular given task. The selection process is done manually, limiting these approaches to smaller resources such as WordNet, which lacks coverage of proper-names and recent terminology. This paper presents a supervised framework for automatically selecting an optimized subset of resource relations for a given target inference task. Our approach enables the use of large-scale knowledge resources, thus providing a rich source of high-precision inferences over proper-names.¹

Original language	English
Title of host publication	CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings
Publisher	Association for Computational Linguistics (ACL)
Pages	175-184
Number of pages	10
ISBN (Electronic)	9781941643778
DOIs	https://doi.org/10.18653/v1/k15-1018
State	Published - 2015
Event	19th Conference on Computational Natural Language Learning, CoNLL 2015 - Beijing, China Duration: 30 Jul 2015 → 31 Jul 2015

Publication series

Name	CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings

Conference

Conference	19th Conference on Computational Natural Language Learning, CoNLL 2015
Country/Territory	China
City	Beijing
Period	30/07/15 → 31/07/15

Bibliographical note

Publisher Copyright:
© 2015 Association for Computational Linguistics.

Funding

This work was supported by an Intel ICRICI grant, the Google Research Award Program and the German Research Foundation via the German-Israeli Project Cooperation (DIP, grant DA 1600/1-1). This work was supported by an Intel ICRI-CI grant, the Google Research Award Program and the German Research Foundation via the German-Israeli Project Cooperation (DIP, grant DA 1600/1-1).

Funders	Funder number
DIP	DA 1600/1-1
German-Israeli Project Cooperation
Google Research Award Program
Intel ICRI-CI
Intel ICRICI
Google
Deutsche Forschungsgemeinschaft
German-Israeli Foundation for Scientific Research and Development

Access to Document

10.18653/v1/k15-1018

Cite this

Shwartz, V., Levy, O., Dagan, I., & Goldberger, J. (2015). Learning to exploit structured resources for lexical inference. In CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings (pp. 175-184). (CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/k15-1018

@inproceedings{998db73660634a7394e874a49d1ff373,

title = "Learning to exploit structured resources for lexical inference",

abstract = "Massive knowledge resources, such as Wikidata, can provide valuable information for lexical inference, especially for proper-names. Prior resource-based approaches typically select the subset of each resource{\textquoteright}s relations which are relevant for a particular given task. The selection process is done manually, limiting these approaches to smaller resources such as WordNet, which lacks coverage of proper-names and recent terminology. This paper presents a supervised framework for automatically selecting an optimized subset of resource relations for a given target inference task. Our approach enables the use of large-scale knowledge resources, thus providing a rich source of high-precision inferences over proper-names.1",

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

note = "Publisher Copyright: {\textcopyright} 2015 Association for Computational Linguistics.; 19th Conference on Computational Natural Language Learning, CoNLL 2015 ; Conference date: 30-07-2015 Through 31-07-2015",

year = "2015",

doi = "10.18653/v1/k15-1018",

language = "אנגלית",

series = "CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings",

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

pages = "175--184",

booktitle = "CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings",

address = "ארצות הברית",

}

Shwartz, V, Levy, O, Dagan, I & Goldberger, J 2015, Learning to exploit structured resources for lexical inference. in CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings. CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings, Association for Computational Linguistics (ACL), pp. 175-184, 19th Conference on Computational Natural Language Learning, CoNLL 2015, Beijing, China, 30/07/15. https://doi.org/10.18653/v1/k15-1018

Learning to exploit structured resources for lexical inference. / Shwartz, Vered; Levy, Omer; Dagan, Ido et al.
CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL), 2015. p. 175-184 (CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings).

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

TY - GEN

T1 - Learning to exploit structured resources for lexical inference

AU - Shwartz, Vered

AU - Levy, Omer

AU - Dagan, Ido

AU - Goldberger, Jacob

PY - 2015

Y1 - 2015

N2 - Massive knowledge resources, such as Wikidata, can provide valuable information for lexical inference, especially for proper-names. Prior resource-based approaches typically select the subset of each resource’s relations which are relevant for a particular given task. The selection process is done manually, limiting these approaches to smaller resources such as WordNet, which lacks coverage of proper-names and recent terminology. This paper presents a supervised framework for automatically selecting an optimized subset of resource relations for a given target inference task. Our approach enables the use of large-scale knowledge resources, thus providing a rich source of high-precision inferences over proper-names.1

AB - Massive knowledge resources, such as Wikidata, can provide valuable information for lexical inference, especially for proper-names. Prior resource-based approaches typically select the subset of each resource’s relations which are relevant for a particular given task. The selection process is done manually, limiting these approaches to smaller resources such as WordNet, which lacks coverage of proper-names and recent terminology. This paper presents a supervised framework for automatically selecting an optimized subset of resource relations for a given target inference task. Our approach enables the use of large-scale knowledge resources, thus providing a rich source of high-precision inferences over proper-names.1

UR - http://www.scopus.com/inward/record.url?scp=85036632428&partnerID=8YFLogxK

U2 - 10.18653/v1/k15-1018

DO - 10.18653/v1/k15-1018

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

AN - SCOPUS:85036632428

T3 - CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings

SP - 175

EP - 184

BT - CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings

PB - Association for Computational Linguistics (ACL)

T2 - 19th Conference on Computational Natural Language Learning, CoNLL 2015

Y2 - 30 July 2015 through 31 July 2015

ER -

Shwartz V, Levy O, Dagan I , Goldberger J. Learning to exploit structured resources for lexical inference. In CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings. Association for Computational Linguistics (ACL). 2015. p. 175-184. (CoNLL 2015 - 19th Conference on Computational Natural Language Learning, Proceedings). doi: 10.18653/v1/k15-1018

Learning to exploit structured resources for lexical inference

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this