End-to-end Relation Extraction using distant supervision from external semantic repositories

Truc Vien T Nguyen, Alessandro Moschitti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

51 Citations (Scopus)

Abstract

In this paper, we extend distant supervision (DS) based on Wikipedia for Relation Extraction (RE) by considering (i) relations defined in external repositories, e.g. YAGO, and (ii) any subset of Wikipedia documents. We show that training data constituted by sentences containing pairs of named entities in target relations is enough to produce reliable supervision. Our experiments with state-of-the-art relation extraction models, trained on the above data, show a meaningful F1 of 74.29% on a manually annotated test set: this highly improves the state-of-art in RE using DS. Additionally, our end-to-end experiments demonstrated that our extractors can be applied to any general text document.

Original languageEnglish
Title of host publicationACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
Pages277-282
Number of pages6
Volume2
Publication statusPublished - 1 Dec 2011
Externally publishedYes
Event49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011 - Portland, OR, United States
Duration: 19 Jun 201124 Jun 2011

Other

Other49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011
CountryUnited States
CityPortland, OR
Period19/6/1124/6/11

Fingerprint

supervision
Wikipedia
semantics
experiment
Repository
Supervision
Experiment
Entity

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Nguyen, T. V. T., & Moschitti, A. (2011). End-to-end Relation Extraction using distant supervision from external semantic repositories. In ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (Vol. 2, pp. 277-282)

End-to-end Relation Extraction using distant supervision from external semantic repositories. / Nguyen, Truc Vien T; Moschitti, Alessandro.

ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 2 2011. p. 277-282.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nguyen, TVT & Moschitti, A 2011, End-to-end Relation Extraction using distant supervision from external semantic repositories. in ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. vol. 2, pp. 277-282, 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011, Portland, OR, United States, 19/6/11.
Nguyen TVT, Moschitti A. End-to-end Relation Extraction using distant supervision from external semantic repositories. In ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 2. 2011. p. 277-282
Nguyen, Truc Vien T ; Moschitti, Alessandro. / End-to-end Relation Extraction using distant supervision from external semantic repositories. ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 2 2011. pp. 277-282
@inproceedings{4f5c03c9a30f43a5aeba39a03844d534,
title = "End-to-end Relation Extraction using distant supervision from external semantic repositories",
abstract = "In this paper, we extend distant supervision (DS) based on Wikipedia for Relation Extraction (RE) by considering (i) relations defined in external repositories, e.g. YAGO, and (ii) any subset of Wikipedia documents. We show that training data constituted by sentences containing pairs of named entities in target relations is enough to produce reliable supervision. Our experiments with state-of-the-art relation extraction models, trained on the above data, show a meaningful F1 of 74.29{\%} on a manually annotated test set: this highly improves the state-of-art in RE using DS. Additionally, our end-to-end experiments demonstrated that our extractors can be applied to any general text document.",
author = "Nguyen, {Truc Vien T} and Alessandro Moschitti",
year = "2011",
month = "12",
day = "1",
language = "English",
isbn = "9781932432886",
volume = "2",
pages = "277--282",
booktitle = "ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies",

}

TY - GEN

T1 - End-to-end Relation Extraction using distant supervision from external semantic repositories

AU - Nguyen, Truc Vien T

AU - Moschitti, Alessandro

PY - 2011/12/1

Y1 - 2011/12/1

N2 - In this paper, we extend distant supervision (DS) based on Wikipedia for Relation Extraction (RE) by considering (i) relations defined in external repositories, e.g. YAGO, and (ii) any subset of Wikipedia documents. We show that training data constituted by sentences containing pairs of named entities in target relations is enough to produce reliable supervision. Our experiments with state-of-the-art relation extraction models, trained on the above data, show a meaningful F1 of 74.29% on a manually annotated test set: this highly improves the state-of-art in RE using DS. Additionally, our end-to-end experiments demonstrated that our extractors can be applied to any general text document.

AB - In this paper, we extend distant supervision (DS) based on Wikipedia for Relation Extraction (RE) by considering (i) relations defined in external repositories, e.g. YAGO, and (ii) any subset of Wikipedia documents. We show that training data constituted by sentences containing pairs of named entities in target relations is enough to produce reliable supervision. Our experiments with state-of-the-art relation extraction models, trained on the above data, show a meaningful F1 of 74.29% on a manually annotated test set: this highly improves the state-of-art in RE using DS. Additionally, our end-to-end experiments demonstrated that our extractors can be applied to any general text document.

UR - http://www.scopus.com/inward/record.url?scp=84859010796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859010796&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781932432886

VL - 2

SP - 277

EP - 282

BT - ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies

ER -