Event extraction as dependency parsing

David McClosky, Mihai Surdeanu, Christopher D. Manning

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

63 Citations (Scopus)

Abstract

Nested event structures are a common occurrence in both open domain and domain specific extraction tasks, e.g., a "crime" event can cause a "investigation" event, which can lead to an "arrest" event. However, most current approaches address event extraction with highly local models that extract each event and argument independently. We propose a simple approach for the extraction of such structures by taking the tree of event-argument relations and using it directly as the representation in a reranking dependency parser. This provides a simple framework that captures global properties of both nested and flat event structures. We explore a rich feature space that models both the events to be parsed and context from the original supporting text. Our approach obtains competitive results in the extraction of biomedical events from the BioNLP'09 shared task with a F1 score of 53.5% in development and 48.6% in testing.

Original languageEnglish (US)
Title of host publicationACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
Pages1626-1635
Number of pages10
Volume1
StatePublished - 2011
Externally publishedYes
Event49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011 - Portland, OR, United States
Duration: Jun 19 2011Jun 24 2011

Other

Other49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011
CountryUnited States
CityPortland, OR
Period6/19/116/24/11

Fingerprint

event
Parsing
offense
cause
Event Structures

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

McClosky, D., Surdeanu, M., & Manning, C. D. (2011). Event extraction as dependency parsing. In ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (Vol. 1, pp. 1626-1635)

Event extraction as dependency parsing. / McClosky, David; Surdeanu, Mihai; Manning, Christopher D.

ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 1 2011. p. 1626-1635.

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

McClosky, D, Surdeanu, M & Manning, CD 2011, Event extraction as dependency parsing. in ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. vol. 1, pp. 1626-1635, 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-HLT 2011, Portland, OR, United States, 6/19/11.
McClosky D, Surdeanu M, Manning CD. Event extraction as dependency parsing. In ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 1. 2011. p. 1626-1635
McClosky, David ; Surdeanu, Mihai ; Manning, Christopher D. / Event extraction as dependency parsing. ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Vol. 1 2011. pp. 1626-1635
@inproceedings{72a982fffe0247acb65c9c15712bda8e,
title = "Event extraction as dependency parsing",
abstract = "Nested event structures are a common occurrence in both open domain and domain specific extraction tasks, e.g., a {"}crime{"} event can cause a {"}investigation{"} event, which can lead to an {"}arrest{"} event. However, most current approaches address event extraction with highly local models that extract each event and argument independently. We propose a simple approach for the extraction of such structures by taking the tree of event-argument relations and using it directly as the representation in a reranking dependency parser. This provides a simple framework that captures global properties of both nested and flat event structures. We explore a rich feature space that models both the events to be parsed and context from the original supporting text. Our approach obtains competitive results in the extraction of biomedical events from the BioNLP'09 shared task with a F1 score of 53.5{\%} in development and 48.6{\%} in testing.",
author = "David McClosky and Mihai Surdeanu and Manning, {Christopher D.}",
year = "2011",
language = "English (US)",
isbn = "9781932432879",
volume = "1",
pages = "1626--1635",
booktitle = "ACL-HLT 2011 - Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies",

}

TY - GEN

T1 - Event extraction as dependency parsing

AU - McClosky, David

AU - Surdeanu, Mihai

AU - Manning, Christopher D.

PY - 2011

Y1 - 2011

N2 - Nested event structures are a common occurrence in both open domain and domain specific extraction tasks, e.g., a "crime" event can cause a "investigation" event, which can lead to an "arrest" event. However, most current approaches address event extraction with highly local models that extract each event and argument independently. We propose a simple approach for the extraction of such structures by taking the tree of event-argument relations and using it directly as the representation in a reranking dependency parser. This provides a simple framework that captures global properties of both nested and flat event structures. We explore a rich feature space that models both the events to be parsed and context from the original supporting text. Our approach obtains competitive results in the extraction of biomedical events from the BioNLP'09 shared task with a F1 score of 53.5% in development and 48.6% in testing.

AB - Nested event structures are a common occurrence in both open domain and domain specific extraction tasks, e.g., a "crime" event can cause a "investigation" event, which can lead to an "arrest" event. However, most current approaches address event extraction with highly local models that extract each event and argument independently. We propose a simple approach for the extraction of such structures by taking the tree of event-argument relations and using it directly as the representation in a reranking dependency parser. This provides a simple framework that captures global properties of both nested and flat event structures. We explore a rich feature space that models both the events to be parsed and context from the original supporting text. Our approach obtains competitive results in the extraction of biomedical events from the BioNLP'09 shared task with a F1 score of 53.5% in development and 48.6% in testing.

UR - http://www.scopus.com/inward/record.url?scp=84859080792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859080792&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781932432879

VL - 1

SP - 1626

EP - 1635

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

ER -