Refining event extraction through cross-document inference

Heng Ji, Ralph Grishman

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

Abstract

We apply the hypothesis of "One Sense Per Discourse" (Yarowsky, 1995) to information extraction (IE), and extend the scope of "discourse" from one single document to a cluster of topically-related documents. We employ a similar approach to propagate consistent event arguments across sentences and documents. Combining global evidence from related documents with local decisions, we design a simple scheme to conduct cross-document inference for improving the ACE event extraction task1. Without using any additional labeled data this new approach obtained 7.6% higher F-Measure in trigger labeling and 6% higher F-Measure in argument labeling over a state-of-the-art IE system which extracts events independently for each sentence.

Original languageEnglish (US)
Title of host publicationACL-08
Subtitle of host publicationHLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
Pages254-262
Number of pages9
StatePublished - 2008
Event46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT - Columbus, OH, United States
Duration: Jun 15 2008Jun 20 2008

Publication series

NameACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

Other

Other46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT
Country/TerritoryUnited States
CityColumbus, OH
Period6/15/086/20/08

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Networks and Communications
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Refining event extraction through cross-document inference'. Together they form a unique fingerprint.

Cite this