Diversity of scenarios in information extraction

Silja Huttunen, Roman Yangarber, Ralph Grishman

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

Abstract

This paper discusses/presents problems of template structure for Information Extraction. We investigate these problems in the context of two new Information Extraction scenarios which are linguistically and structurally more challenging than the traditional MUC scenarios. By a scenario we mean a predefined set of facts to be extracted from text. Traditional views on event structure and template design are not adequate for the more complex scenarios. We identify two structural factors that contribute to the complexity of a scenario: first, the scattering of events in text, and second, inclusion relationship between events. These factors cause difficulty in representing the facts in an unambiguous way. Traditional views on event structure and template design are not adequate for the more complex scenarios. We propose that these kinds of event relationships can be better described with a modular, hierarchical model.

Original languageEnglish (US)
Title of host publicationProceedings of the 3rd International Conference on Language Resources and Evaluation, LREC 2002
PublisherEuropean Language Resources Association (ELRA)
Pages1443-1450
Number of pages8
StatePublished - Jan 1 2002
Event3rd International Conference on Language Resources and Evaluation, LREC 2002 - Las Palmas, Canary Islands, Spain
Duration: May 29 2002May 31 2002

Other

Other3rd International Conference on Language Resources and Evaluation, LREC 2002
CountrySpain
CityLas Palmas, Canary Islands
Period5/29/025/31/02

Fingerprint

scenario
event
Scenarios
Information Extraction
inclusion
cause
Template
Event Structures

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics
  • Education
  • Library and Information Sciences

Cite this

Huttunen, S., Yangarber, R., & Grishman, R. (2002). Diversity of scenarios in information extraction. In Proceedings of the 3rd International Conference on Language Resources and Evaluation, LREC 2002 (pp. 1443-1450). European Language Resources Association (ELRA).

Diversity of scenarios in information extraction. / Huttunen, Silja; Yangarber, Roman; Grishman, Ralph.

Proceedings of the 3rd International Conference on Language Resources and Evaluation, LREC 2002. European Language Resources Association (ELRA), 2002. p. 1443-1450.

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

Huttunen, S, Yangarber, R & Grishman, R 2002, Diversity of scenarios in information extraction. in Proceedings of the 3rd International Conference on Language Resources and Evaluation, LREC 2002. European Language Resources Association (ELRA), pp. 1443-1450, 3rd International Conference on Language Resources and Evaluation, LREC 2002, Las Palmas, Canary Islands, Spain, 5/29/02.
Huttunen S, Yangarber R, Grishman R. Diversity of scenarios in information extraction. In Proceedings of the 3rd International Conference on Language Resources and Evaluation, LREC 2002. European Language Resources Association (ELRA). 2002. p. 1443-1450
Huttunen, Silja ; Yangarber, Roman ; Grishman, Ralph. / Diversity of scenarios in information extraction. Proceedings of the 3rd International Conference on Language Resources and Evaluation, LREC 2002. European Language Resources Association (ELRA), 2002. pp. 1443-1450
@inproceedings{9c69fce5f29e493ba8a7a002ee378a7d,
title = "Diversity of scenarios in information extraction",
abstract = "This paper discusses/presents problems of template structure for Information Extraction. We investigate these problems in the context of two new Information Extraction scenarios which are linguistically and structurally more challenging than the traditional MUC scenarios. By a scenario we mean a predefined set of facts to be extracted from text. Traditional views on event structure and template design are not adequate for the more complex scenarios. We identify two structural factors that contribute to the complexity of a scenario: first, the scattering of events in text, and second, inclusion relationship between events. These factors cause difficulty in representing the facts in an unambiguous way. Traditional views on event structure and template design are not adequate for the more complex scenarios. We propose that these kinds of event relationships can be better described with a modular, hierarchical model.",
author = "Silja Huttunen and Roman Yangarber and Ralph Grishman",
year = "2002",
month = "1",
day = "1",
language = "English (US)",
pages = "1443--1450",
booktitle = "Proceedings of the 3rd International Conference on Language Resources and Evaluation, LREC 2002",
publisher = "European Language Resources Association (ELRA)",

}

TY - GEN

T1 - Diversity of scenarios in information extraction

AU - Huttunen, Silja

AU - Yangarber, Roman

AU - Grishman, Ralph

PY - 2002/1/1

Y1 - 2002/1/1

N2 - This paper discusses/presents problems of template structure for Information Extraction. We investigate these problems in the context of two new Information Extraction scenarios which are linguistically and structurally more challenging than the traditional MUC scenarios. By a scenario we mean a predefined set of facts to be extracted from text. Traditional views on event structure and template design are not adequate for the more complex scenarios. We identify two structural factors that contribute to the complexity of a scenario: first, the scattering of events in text, and second, inclusion relationship between events. These factors cause difficulty in representing the facts in an unambiguous way. Traditional views on event structure and template design are not adequate for the more complex scenarios. We propose that these kinds of event relationships can be better described with a modular, hierarchical model.

AB - This paper discusses/presents problems of template structure for Information Extraction. We investigate these problems in the context of two new Information Extraction scenarios which are linguistically and structurally more challenging than the traditional MUC scenarios. By a scenario we mean a predefined set of facts to be extracted from text. Traditional views on event structure and template design are not adequate for the more complex scenarios. We identify two structural factors that contribute to the complexity of a scenario: first, the scattering of events in text, and second, inclusion relationship between events. These factors cause difficulty in representing the facts in an unambiguous way. Traditional views on event structure and template design are not adequate for the more complex scenarios. We propose that these kinds of event relationships can be better described with a modular, hierarchical model.

UR - http://www.scopus.com/inward/record.url?scp=33845969435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33845969435&partnerID=8YFLogxK

M3 - Conference contribution

SP - 1443

EP - 1450

BT - Proceedings of the 3rd International Conference on Language Resources and Evaluation, LREC 2002

PB - European Language Resources Association (ELRA)

ER -