[Corpora-List] Call for papers: Workshop on language processing in the biomedical domain

Fri Feb 25 14:16:19 UTC 2005

Hi, CORPORA list people,

The list of topics for this meeting includes a number of areas of
interest to corpus linguists, including:

- corpus construction efforts
- evaluation and testing of systems
- test suites for biomedical language processing systems

It's being held in Detroit, MI, the day before the ACL Tutorial Day.

Workshop title: Linking Biological Literature, Ontologies and
Databases: Mining Biological Semantics

Description

This workshop will bring researchers in natural language processing in
the bioinformatics and biomedical domains together with scientists in
bioinformatics and biology.  It follows successful workshops on the
topic at ACL 2002, 2003, and 2004, and NAACL 2004, as well as related
meetings at PSB (Pacific Symposium on Biocomputing) and ISMB
(Intelligent Systems in Molecular Biology).  This will be a joint
workshop with the ISMB SIG on text mining for biology, and it will be
colocated with the ISCB annual meeting in Detroit, MI, on June 24,
2005.

Recent years have seen an interesting confluence between the worlds of
bioinformatics and natural language processing.  Molecular biologists,
confronted with new high-throughput sources of data, have recognized
that language processing can provide them with tools for handling a
flood of data that is unprecedented in the history of the life
sciences.  The natural language processing community, in turn, has
become aware of the resources that the computational bioscience
community has made available, and there has been growing interest in
applying natural language processing techniques to mine the biological
literature to support complex applications in the biological domain,
ranging from identifying relevant literature (information retrieval)
to extraction of experimental finding to populate biological knowledge
bases to summarization, to present key facts to biologists in succinct
form.

A number of successful conferences and workshops have resulted, with
significant progress in the areas of entity identification, concept
normalization, and system evaluation coming through competitions like
the KDD Cup, BioCreAtIvE and through shared resources like the Genia
corpus.

This workshop will continue the interaction between these communities.
Papers on the role of ontologies in understanding biomedical texts
and on evaluation and testing of systems built for these domains are
especially invited, but submissions on all topics related to natural
language processing in the bioinformatics, biomedicine, and molecular
biology are welcome, including:

- the role of ontologies and knowledge bases in understanding biomedical texts
- knowledge representation
- evaluation and testing of systems
- test suites for biomedical language processing systems
- entity identification and normalization
- information extraction
- information retrieval
- corpus construction efforts
- coreference and anaphora resolution
- visualization

Target audience and expected number of participants

The target audience is researchers in natural language processing in
the molecular biology, medical, and associated domains.  We expect
these researchers to come from the fields of linguistics, computer
science, bioinformatics, medical informatics, and molecular biology.

The expected number of participants is 70.

Workshop length

The workshop length will be one day.

Organizing committee

Kevin Bretonnel Cohen leads the Biomedical Text Mining Group at the
University of Colorado's Center for Computational Pharmacology.  He is
the author of a number of papers and one book chapter on natural
language processing in the biomedical domain.  Current projects in the
Center for Computational Pharmacology include an NIH R-01-funded
project to build a molecular biology knowledgebase using text data
mining; an information extraction project targeting assertions about
translocation of proteins; and ongoing research in software testing
techniques for natural language processing software.

Lynette Hirschman is Chief Scientist for the Information Technology
Center at MITRE in Bedford, MA, where she leads MITRE's efforts in
bioinformatics and text mining for biology.  Her group has been
responsible for the 2002 KDD Challenge Cup Evaluation Task 1:
Information Extraction for Biomedical Articles and the 2004
BioCreAtIvE challenge evaluation in biomedical entity extraction (in
conjunction with Alfonso Valencia and Christian Blaschke at the Centro
Nacional de Biotechnología).  Recent research projects have included
the use of curated biological databases for noisy training data to
train statistical entity extraction systems, and tools to aid curators
for biological databases. She is the co-organizer of the ISMB Special
Interest Group on Text Mining for Biology (with Alfonso Valencia) and
is currently serving on the Gene Ontology Consortium Advisory
Committee.

Christian Blaschke is the project leader for text mining and
information extraction systems at bioalma in Madrid.  He was the first
author of the earliest paper on rule-based information extraction from
molecular biology literature.  His recent projects have included being
an organizer of the first BioCreative (Critical Assessment of
Information Extraction Systems in Biology) competition on biological
text data mining.  His current work involves leading the development
of text mining systems for pharmaceutical and biotechnology companies.

Hagit Shatkay is an assistant professor in the School of Computing at
Queen's University in Kingston, Ontario.  Her research is in the area
of machine learning as it applies to biomedical data mining.  She is
an active member of the biomedical text-mining research community,
where her work focuses on biomedical information retrieval.  She has
presented tutorials on biomedical literature mining at the Pacific
Symposium on Biocomputing, the Bioinformatics Summer School, and the
International Conference on Intelligent Systems for Molecular Biology,
and has recently established BLIMP, a web-based forum for Biomedical
Literature Mining Publications.  Prior to joining Queen's University,
she was a researcher with the Informatics Research group at
Celera/Applied Biosystems, following a postdoctoral fellowship at the
National Center for Biotechnology Information.  She holds a PhD in
computer science from Brown University, and an MSc and BSc in computer
science from the Hebrew University in Jerusalem.

Program Committee

We have assembled a strong set of people from academia, industry, and
government in the US, Europe, and Japan.  The program committee
includes researchers with world-class reputations in this field.

Sophia Ananiadou, University of Salford
Lan Aronson, NLM
Breck Baldwin, Alias-i Inc.
Olivier Bodenreider, NLM
Shannon Bradshaw, University of Iowa
Bob Carpenter, Alias-i Inc.
Jeff Chang, Duke Univeristy
Aaron Cohen, Oregon Health Sciences University
Nigel Collier, National Institute of Informatics, Japan
Lynne Fox, University of Colorado Health Sciences Center
Bob Futrelle, Northeastern University
Henk Harkema, University of Sheffield
Marti Hearst, University of California at Berkeley
Larry Hunter, University of Colorado School of Medicine
Steve Johnson, Columbia University
Marc Light, University of Iowa
Hongfang Liu, University of Maryland at Baltimore County
Alex Morgan, MITRE
James Pustejovsky, Brandeis University
Tom Rindflesch, NLM
Andrey Rzhetsky, Columbia University
Jasmin Saric, EML Research gGmbH
Lorrie Tanabe, NCBI, NLM
Jun-ichi Tsujii, University of Tokyo
Alfonso Valencia, Universidad Autonoma de Madrid
Karin Verspoor, Los Alamos National Labs
John Wilbur, NCBI, NLM
Hong Yu, Columbia University

--
K. B. Cohen
Biomedical Text Mining Group Lead
Center for Computational Pharmacology
303-916-2417 (cell) 303-377-9194 (home)
http://compbio.uchsc.edu/Hunter_lab/Cohen
http://www.ling.ohio-state.edu/~kcohen/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20050225/aea80c27/attachment.htm>