BioNLP Shared Task 2011

News

  • BMC Bioinformatics special issue on BioNLP Shared Task 2011 published.
  • Some evaluation services down for server relocation
    • The evaluation services for the following tasks are now back up: GE, EPI, ID
    • Other online evaluation services are temporarily down for server relocation. We hope to have them running again soon and apologize for any inconvenience.
  • Updated data visualisations
  • Correction to ID task CORE results - details
  • Special Issue of BMC Bioinformatics - CFPs
  • BioNLP-ST 2011 resources released to public
  • BioNLP-ST 2011 visualisation tool v1.0 released

Introduction

The BioNLP Shared Task series represents a community-wide move in bio-textmining toward fine-grained information extraction (IE). The first event, the BioNLP 2009 shared task (Dec. 2008-March 2009), attracted wide attention, with 24 teams submitting final results. The task setup and data have since served as the basis of numerous studies and published event extraction systems and datasets. The BioNLP Shared Task 2011 (BioNLP-ST'11) is the follow-up event to the BioNLP 2009 shared task. While following the general outline and goals of the previous task in defining biologically relevant extraction targets and a linguistically motivated approach to event representation, the upcoming task will generalize and extend on the previous in three key aspects: text type, domain, and targeted event types. Manually annotated data where all annotations are bound to specific expressions in text will be provided for training, development and evaluation of extraction methods, and tools for detailed evaluation of system outputs will be made available. Participation to the task is open to all interested parties.

Tasks

Main Tasks

While the BioNLP 2009 shared task relied on the GENIA corpus which contained PubMed abstracts on transcription factors in human blood cells, the theme of BioNLP-ST 2011 is generalization, which will be pursued to three directions: text types, event types, and subject domains. To achieve that, various tasks and annotations were created in collaboration between several groups, and event extraction tasks are arranged in four tracks.


Supporting Tasks

BioNLP-ST 2011 also includes three supporting tasks.

Although they are not event extraction tasks themselves, according to the analysis on the results of BioNLP 2009 shared task, co-reference resolution and entity relation detection are expected to play an important role in making a breakthrough in improving event extraction performance. Gene renaming has similar feature with co-references.

Resources

 Task Description Data sets Online evaluation
 GEhome Downloads development set  test set
 EPIhome  development set  test set
 IDhome  development set  test set
 BBhome  development set  test set
 BIhome  development set  test set
 COhome  development set  test set
 RELhome  development set  test set
 RENhome  development set  test set

You need to be registered to use the test set online evaluation.
Each registered user can use test set online evaluation of each task once per a day.

Links

Organization

Scientific Advisory Committee

  • Jun’ichi Tsujii (Chair), University of  Tokyo, and National Centre for Text Mining (NaCTeM)
  • Sophia Ananiadou, National Centre for Text Mining (NaCTeM)
  • Kevin Cohen, University of Colorado, and MITRE
  • Claire Nedellec, French National Institute for Agricultural Research (INRA)
  • Andrey Rzhetsky, University of Chicago
  • Bruno Sobral, Virginia Bioinformatics Institute
  • Tapio Salakoski, University of Turku
  • Toshihisa Takagi, Database Center for Life Science (DBCLS)

Organizing Committee

  • Jin-Dong Kim (Chair), Database Center for Life Science (DBCLS)
  • Sampo Pyysalo (Chair), University of  Tokyo
  • Tomoko Ohta, University of Tokyo
  • Robert Bossy, French National Institute for Agricultural Research (INRA)
  • Chunhong Mao, Virginia Bioinformatics Institute
  • Dan Sullivan, Virginia Bioinformatics Institute
  • Rafal Rak,  National Centre for Text Mining (NaCTeM)
  • Nguyen Luu Thuy Ngan, University of Tokyo

Program Committee

  • Timothy Baldwin, University of Melbourne
  • Sabine Bergler, Concordia University
  • Olivier Bodenreider, National Library of Medicine (NLM)
  • Wendy Chapman, University of California, San Diego (UCSD)
  • Kevin Cohen, University of Colorado, and MITRE
  • Nigel Collier, National Institute of Informatics (NII)
  • Filip Ginter, University of Turku
  • Jörg Hakenberg, Arizona State University
  • Minlie Huang, Tsinghua University
  • Su Jian, Institute for Infocomm Research
  • Min-Yen Kan, National University of Singapore
  • Jung-Jae Kim, Nanyang Technological University
  • Martin Krallinger, National Biotechnology Center (CNB)
  • Zhiyong Lu, National Library of Medicine (NLM)
  • David McClosky, Stanford University
  • Roser Morante, University of Antwerp
  • Claire Nedellec, French National Institute for Agricultural Research (INRA)
  • Serguei Pakhomov, University of Minnesota
  • Thierry Poibeau, French Institute for Fundamental Research (CNRS)
  • Hoifung Poon, University of Washington
  • Sebastian Riedel, University of Massachusetts
  • Fabio Rinaldi, University of Zurich
  • Thomas Rindflesch, National Library of Medicine (NLM)
  • Yvan Saeys, Ghent University
  • Tapio Salakoski, University of Turku
  • Hagit Shatkay, University of Delaware
  • Rune Sætre, Norwegian University of Science and Technology (NTNU)
  • Yuka Tateisi, Kogakuin University
  • Yoshimasa Tsuruoka, Japan Advanced Institute of Science and Technology (JAIST)
  • Karin Verspoor, University of Colorado
  • Xinglong Wang, National Centre for Text Mining
  • Hong Yu, University of Wisconsin-Milwaukee
  • Pierre Zweigenbaum, French National Center for Scientific Research (CNRS)

Contacts