Combining Global Relevance Information with Local Contextual Clues for Event-Oriented Information Extraction

Siddharth Patwardhan

Existing Information Extraction (IE) systems tend to focus on a tight window of context surrounding the desired information to be extracted. This research addresses shortcomings of these systems by introducing a two-phase approach to IE that incorporates global relevance information with local contextual evidence, to effectively extract information from free text.

Subjects: 13. Natural Language Processing; Please choose a second document classification

Submitted: Apr 7, 2008

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.