Using predicate-argument structures for information extraction

Mihai Surdeanu; Sanda Harabagiu; John Williams; Paul Aarseth

Using predicate-argument structures for information extraction

Mihai Surdeanu, Sanda Harabagiu, John Williams, Paul Aarseth

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper we present a novel, customizable IE paradigm that takes advantage of predicate-argument structures. We also introduce a new way of automatically identifying predicate argument structures, which is central to our IE paradigm. It is based on: (1) an extended set of features; and (2) inductive decision tree learning. The experimental results prove our claim that accurate predicate-argument structures enable high quality IE results.

Original language	English (US)
Journal	Proceedings of the Annual Meeting of the Association for Computational Linguistics
Volume	2003-July
State	Published - 2003
Externally published	Yes
Event	41st Annual Meeting of the Association for Computational Linguistics, ACL 2003 - Sapporo, Japan Duration: Jul 7 2003 → Jul 12 2003

ASJC Scopus subject areas

Computer Science Applications
Linguistics and Language
Language and Linguistics

Cite this

@article{93cbafe6c8e748ebb8c74e67606e1a5c,

title = "Using predicate-argument structures for information extraction",

abstract = "In this paper we present a novel, customizable IE paradigm that takes advantage of predicate-argument structures. We also introduce a new way of automatically identifying predicate argument structures, which is central to our IE paradigm. It is based on: (1) an extended set of features; and (2) inductive decision tree learning. The experimental results prove our claim that accurate predicate-argument structures enable high quality IE results.",

author = "Mihai Surdeanu and Sanda Harabagiu and John Williams and Paul Aarseth",

note = "Publisher Copyright: {\textcopyright} ACL 2003.All right reserved.; 41st Annual Meeting of the Association for Computational Linguistics, ACL 2003 ; Conference date: 07-07-2003 Through 12-07-2003",

year = "2003",

language = "English (US)",

volume = "2003-July",

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

issn = "0736-587X",

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

}

TY - JOUR

T1 - Using predicate-argument structures for information extraction

AU - Surdeanu, Mihai

AU - Harabagiu, Sanda

AU - Williams, John

AU - Aarseth, Paul

PY - 2003

Y1 - 2003

N2 - In this paper we present a novel, customizable IE paradigm that takes advantage of predicate-argument structures. We also introduce a new way of automatically identifying predicate argument structures, which is central to our IE paradigm. It is based on: (1) an extended set of features; and (2) inductive decision tree learning. The experimental results prove our claim that accurate predicate-argument structures enable high quality IE results.

AB - In this paper we present a novel, customizable IE paradigm that takes advantage of predicate-argument structures. We also introduce a new way of automatically identifying predicate argument structures, which is central to our IE paradigm. It is based on: (1) an extended set of features; and (2) inductive decision tree learning. The experimental results prove our claim that accurate predicate-argument structures enable high quality IE results.

UR - http://www.scopus.com/inward/record.url?scp=85149133991&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85149133991&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85149133991

SN - 0736-587X

VL - 2003-July

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

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

T2 - 41st Annual Meeting of the Association for Computational Linguistics, ACL 2003

Y2 - 7 July 2003 through 12 July 2003

ER -

Using predicate-argument structures for information extraction

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this