International Joint Workshop on Natural Language Processing in Biomedicine and its Applications
 
lugar Ginebra
dir cod pais Suiza
Inicio:  28 agosto 2004
Fin:  29 agosto 2004
Convocatoria:  hasta el 14-4-2004
 
  Comentarios:
Workshop Description

This year NLPBA (http://www.genisis.ch/~natlang/NLPBA02/) and BioNLP
(http://www-tsujii.is.s.u-tokyo.ac.jp/ACL03/bionlp.htm) merge for a
joint workshop with the aim of bringing together researchers from
natural language processing, bio-informatics, medicine and ontologies
who are concerned with developing methods and resources for solving
these problems.

Over the last five years we have seen significant steps forward in the
development of language technology and large-scale resources for the
Bio-Medical domain such as linguistically annotated corpora
(e.g. GENIA POS and NE corpora), ontologies (e.g. Gene Ontology),
thesauri (e.g. UMLS Metathesaurus), lexicons and term lists (e.g. UMLS
SPECIALIST) as well as information retrieval collections (e.g. TREC
Genomics track). At the application level we see development of
question answering systems, event recognition, zone (rhetorical
region) identification, as well as term and bio-entity
recognition. The demand for information access tools from domain users
is increasing to support literature survey, often integrated into
online ?portals? where scientists can navigate through related
information resources such as genetics and disease databases. Ongoing
challenges relate to the growing and ambiguous nomenclature, the need
to integrate deep knowledge sources into machine learning, a need to
scale up methods for processing full text articles etc.

The objective of the workshop is to bring together researchers in this
area, to establish common themes and goals between different
groups. We have seen from previous experience in the natural language
learning and information retrieval communities the benefits of sharing
resources and developing common evaluation criteria. In this workshop
we are introducing a special shared task to promote discussion of
these issues as well as the objective of integrating machine learning
with knowledge resources.

We invite submission of papers on topics related to bio-medical NLP
including, but not limited to:

* Information extraction
* Text mining
* Named entity recognition
* Coreference resolution
* Term recognition
* Knowledge-based information retrieval
* Multi-lingual resources and applications
* Ontology construction and ontology mapping
* Visualization tools for viewing clustered or extracted information or meta-data
* Multi-modal approaches combining text and images, etc.
* Event recognition
* Construction of pathways from literature and databases
* Creation of data-sets of bio-medical entities, coreferences and relations
* Annotation standards and quality control methodologies
* Resource integration and re-engineering
* Corpus/lexicon construction
* Text summarization and report generation

Shared Task

This year we propose to have a special shared task: bio-medical named
entity recognition from the GENIA corpus. The purpose of this track is
essentially to investigate the integration of statistical machine
learning methods with symbolic knowledge sources from the bio-medical
domain such as ontologies, thesauri and lexicons : shared task
description.

Paper Format and Submission

Papers must follow the COLING 2004 templates, and will be submitted by
email to jnlpba-submit@david.hcuge.ch.

Important Dates

· Submission deadline for workshop papers: April 14th, 2004
· Notification of accepted papers: May 14th, 2004
· Deadline for camera ready copies: June 6th, 2004

Contact Information

General organization : jnlpba-request@david.hcuge.ch
Shared task organization: bio04sharedtask@nii.ac.jp