Leveraging dependency regularization for event extraction

Kai Cao, Xiang Li, Ralph Grishman

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

Abstract

Event Extraction (EE) is a challenging Information Extraction task which aims to discover event triggers with specific types and their arguments. Most recent research on Event Extraction relies on pattern-based or feature-based approaches, trained on annotated corpora, to recognize combinations of event triggers, arguments, and other contextual information. These combinations may each appear in a variety of linguistic forms. Not all of these event expressions will have appeared in the training data, thus adversely affecting EE performance. In this paper, we demonstrate the overall effectiveness of Dependency Regularization techniques to generalize the patterns extracted from the training data to boost EE performance. We present experimental results on the ACE 2005 corpus, showing improvement over the baseline system, and consider the impact of the individual regularization rules.

Original languageEnglish (US)
Title of host publicationProceedings of the 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016
PublisherAAAI Press
Pages20-25
Number of pages6
ISBN (Electronic)9781577357568
StatePublished - 2016
Event29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016 - Key Largo, United States
Duration: May 16 2016May 18 2016

Other

Other29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016
CountryUnited States
CityKey Largo
Period5/16/165/18/16

Fingerprint

Linguistics

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Cao, K., Li, X., & Grishman, R. (2016). Leveraging dependency regularization for event extraction. In Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016 (pp. 20-25). AAAI Press.

Leveraging dependency regularization for event extraction. / Cao, Kai; Li, Xiang; Grishman, Ralph.

Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016. AAAI Press, 2016. p. 20-25.

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

Cao, K, Li, X & Grishman, R 2016, Leveraging dependency regularization for event extraction. in Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016. AAAI Press, pp. 20-25, 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016, Key Largo, United States, 5/16/16.
Cao K, Li X, Grishman R. Leveraging dependency regularization for event extraction. In Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016. AAAI Press. 2016. p. 20-25
Cao, Kai ; Li, Xiang ; Grishman, Ralph. / Leveraging dependency regularization for event extraction. Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016. AAAI Press, 2016. pp. 20-25
@inproceedings{3bbec1a2ea0642b68733a74794d3a6a9,
title = "Leveraging dependency regularization for event extraction",
abstract = "Event Extraction (EE) is a challenging Information Extraction task which aims to discover event triggers with specific types and their arguments. Most recent research on Event Extraction relies on pattern-based or feature-based approaches, trained on annotated corpora, to recognize combinations of event triggers, arguments, and other contextual information. These combinations may each appear in a variety of linguistic forms. Not all of these event expressions will have appeared in the training data, thus adversely affecting EE performance. In this paper, we demonstrate the overall effectiveness of Dependency Regularization techniques to generalize the patterns extracted from the training data to boost EE performance. We present experimental results on the ACE 2005 corpus, showing improvement over the baseline system, and consider the impact of the individual regularization rules.",
author = "Kai Cao and Xiang Li and Ralph Grishman",
year = "2016",
language = "English (US)",
pages = "20--25",
booktitle = "Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016",
publisher = "AAAI Press",

}

TY - GEN

T1 - Leveraging dependency regularization for event extraction

AU - Cao, Kai

AU - Li, Xiang

AU - Grishman, Ralph

PY - 2016

Y1 - 2016

N2 - Event Extraction (EE) is a challenging Information Extraction task which aims to discover event triggers with specific types and their arguments. Most recent research on Event Extraction relies on pattern-based or feature-based approaches, trained on annotated corpora, to recognize combinations of event triggers, arguments, and other contextual information. These combinations may each appear in a variety of linguistic forms. Not all of these event expressions will have appeared in the training data, thus adversely affecting EE performance. In this paper, we demonstrate the overall effectiveness of Dependency Regularization techniques to generalize the patterns extracted from the training data to boost EE performance. We present experimental results on the ACE 2005 corpus, showing improvement over the baseline system, and consider the impact of the individual regularization rules.

AB - Event Extraction (EE) is a challenging Information Extraction task which aims to discover event triggers with specific types and their arguments. Most recent research on Event Extraction relies on pattern-based or feature-based approaches, trained on annotated corpora, to recognize combinations of event triggers, arguments, and other contextual information. These combinations may each appear in a variety of linguistic forms. Not all of these event expressions will have appeared in the training data, thus adversely affecting EE performance. In this paper, we demonstrate the overall effectiveness of Dependency Regularization techniques to generalize the patterns extracted from the training data to boost EE performance. We present experimental results on the ACE 2005 corpus, showing improvement over the baseline system, and consider the impact of the individual regularization rules.

UR - http://www.scopus.com/inward/record.url?scp=85004010428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85004010428&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85004010428

SP - 20

EP - 25

BT - Proceedings of the 29th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2016

PB - AAAI Press

ER -