Including new patterns to improve event extraction systems

Kai Cao, Xiang Li, Weicheng Ma, 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 of specific types along with 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. However, as the event instances in the ACE corpus are not evenly distributed, some frequent expressions involving ACE event triggers do not appear in the training data, adversely affecting the performance. In this paper, we demonstrate the effectiveness of systematically importing expert-level patterns from TABARI to boost EE performance. The experimental results demonstrate that our pattem-based system with the expanded patterns can achieve 69.8% (with 1.9% absolute improvement) F-measure over the baseline, an advance over current state-of-the-art systems.

Original languageEnglish (US)
Title of host publicationProceedings of the 31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018
EditorsKeith Brawner, Vasile Rus
PublisherAAAI press
Pages487-492
Number of pages6
ISBN (Electronic)9781577357964
StatePublished - 2018
Event31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018 - Melbourne, United States
Duration: May 21 2018May 23 2018

Publication series

NameProceedings of the 31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018

Conference

Conference31st International Florida Artificial Intelligence Research Society Conference, FLAIRS 2018
Country/TerritoryUnited States
CityMelbourne
Period5/21/185/23/18

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Fingerprint

Dive into the research topics of 'Including new patterns to improve event extraction systems'. Together they form a unique fingerprint.

Cite this