Overview of BioNLP'09 shared task on event extraction

  • Authors:
  • Jin-Dong Kim;Tomoko Ohta;Sampo Pyysalo;Yoshinobu Kano;Jun'ichi Tsujii

  • Affiliations:
  • University of Tokyo, Tokyo, Japan;University of Tokyo, Tokyo, Japan;University of Tokyo, Tokyo, Japan;University of Tokyo, Tokyo, Japan;University of Tokyo, Tokyo, Japan and University of Manchester, Manchester, UK

  • Venue:
  • BioNLP '09 Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing: Shared Task
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper presents the design and implementation of the BioNLP'09 Shared Task, and reports the final results with analysis. The shared task consists of three sub-tasks, each of which addresses bio-molecular event extraction at a different level of specificity. The data was developed based on the GENIA event corpus. The shared task was run over 12 weeks, drawing initial interest from 42 teams. Of these teams, 24 submitted final results. The evaluation results are encouraging, indicating that state-of-the-art performance is approaching a practically applicable level and revealing some remaining challenges.