Improving event detection with active learning

Kai Cao, Xiang Li, Miao Fan, Ralph Grishman

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

Abstract

Event Detection (ED), one aspect of Information Extraction, involves identifying instances of specified types of events in text. Much of the research on ED has been based on the specifications of the 2005 ACE [Automatic Content Extraction] event task1, and the associated annotated corpus. However, as the event instances in the ACE corpus are not evenly distributed, some frequent expressions involving ACE events do not appear in the training data, adversely affecting performance. In this paper, we demonstrate the effectiveness of a Pattern Expansion technique to import frequent patterns extracted from external corpora to boost ED performance. The experimental results show that our pattern-based system with the expanded patterns can achieve 70.4% (with 1.6% absolute improvement) F-measure over the baseline, an advance over current state-of-the-art systems.

Original languageEnglish (US)
Title of host publicationInternational Conference Recent Advances in Natural Language Processing, RANLP
PublisherAssociation for Computational Linguistics (ACL)
Pages72-77
Number of pages6
Volume2015-January
StatePublished - 2015
Event10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015 - Hissar, Bulgaria
Duration: Sep 7 2015Sep 9 2015

Other

Other10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015
CountryBulgaria
CityHissar
Period9/7/159/9/15

Fingerprint

Specifications
Problem-Based Learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Cite this

Cao, K., Li, X., Fan, M., & Grishman, R. (2015). Improving event detection with active learning. In International Conference Recent Advances in Natural Language Processing, RANLP (Vol. 2015-January, pp. 72-77). Association for Computational Linguistics (ACL).

Improving event detection with active learning. / Cao, Kai; Li, Xiang; Fan, Miao; Grishman, Ralph.

International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2015-January Association for Computational Linguistics (ACL), 2015. p. 72-77.

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

Cao, K, Li, X, Fan, M & Grishman, R 2015, Improving event detection with active learning. in International Conference Recent Advances in Natural Language Processing, RANLP. vol. 2015-January, Association for Computational Linguistics (ACL), pp. 72-77, 10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015, Hissar, Bulgaria, 9/7/15.
Cao K, Li X, Fan M, Grishman R. Improving event detection with active learning. In International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2015-January. Association for Computational Linguistics (ACL). 2015. p. 72-77
Cao, Kai ; Li, Xiang ; Fan, Miao ; Grishman, Ralph. / Improving event detection with active learning. International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2015-January Association for Computational Linguistics (ACL), 2015. pp. 72-77
@inproceedings{fcc97f555f8e42ea98893268e4963d0f,
title = "Improving event detection with active learning",
abstract = "Event Detection (ED), one aspect of Information Extraction, involves identifying instances of specified types of events in text. Much of the research on ED has been based on the specifications of the 2005 ACE [Automatic Content Extraction] event task1, and the associated annotated corpus. However, as the event instances in the ACE corpus are not evenly distributed, some frequent expressions involving ACE events do not appear in the training data, adversely affecting performance. In this paper, we demonstrate the effectiveness of a Pattern Expansion technique to import frequent patterns extracted from external corpora to boost ED performance. The experimental results show that our pattern-based system with the expanded patterns can achieve 70.4{\%} (with 1.6{\%} absolute improvement) F-measure over the baseline, an advance over current state-of-the-art systems.",
author = "Kai Cao and Xiang Li and Miao Fan and Ralph Grishman",
year = "2015",
language = "English (US)",
volume = "2015-January",
pages = "72--77",
booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Improving event detection with active learning

AU - Cao, Kai

AU - Li, Xiang

AU - Fan, Miao

AU - Grishman, Ralph

PY - 2015

Y1 - 2015

N2 - Event Detection (ED), one aspect of Information Extraction, involves identifying instances of specified types of events in text. Much of the research on ED has been based on the specifications of the 2005 ACE [Automatic Content Extraction] event task1, and the associated annotated corpus. However, as the event instances in the ACE corpus are not evenly distributed, some frequent expressions involving ACE events do not appear in the training data, adversely affecting performance. In this paper, we demonstrate the effectiveness of a Pattern Expansion technique to import frequent patterns extracted from external corpora to boost ED performance. The experimental results show that our pattern-based system with the expanded patterns can achieve 70.4% (with 1.6% absolute improvement) F-measure over the baseline, an advance over current state-of-the-art systems.

AB - Event Detection (ED), one aspect of Information Extraction, involves identifying instances of specified types of events in text. Much of the research on ED has been based on the specifications of the 2005 ACE [Automatic Content Extraction] event task1, and the associated annotated corpus. However, as the event instances in the ACE corpus are not evenly distributed, some frequent expressions involving ACE events do not appear in the training data, adversely affecting performance. In this paper, we demonstrate the effectiveness of a Pattern Expansion technique to import frequent patterns extracted from external corpora to boost ED performance. The experimental results show that our pattern-based system with the expanded patterns can achieve 70.4% (with 1.6% absolute improvement) F-measure over the baseline, an advance over current state-of-the-art systems.

UR - http://www.scopus.com/inward/record.url?scp=84949813368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949813368&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2015-January

SP - 72

EP - 77

BT - International Conference Recent Advances in Natural Language Processing, RANLP

PB - Association for Computational Linguistics (ACL)

ER -