Natural Language Processing in the Biomedical Domain
Association for Computational Linguistics 2002 ( ACL-02 )

July 11
University of Pennsylvania
Philadelphia, PA

Workshop Description

The aim of this workshop is to focus on challenges in processing biomedical language and to present results in developing techniques for this domain. Biomedicine comprises biological sciences, clinical medicine, public health and education. This domain presents many opportunities for NLP technologies such as information extraction from biomedical texts, document and answer retrieval from large, unstructured text collections (such as the biomedical literature and the World Wide Web), and interaction with users through natural language. Until recently, the level of collaboration between core computational linguistics researchers and the biomedical informatics community has been limited. The purpose of this workshop is to take active steps towards bridging that gap. Indeed, this is the first workshop under the auspices of the ACL entirely devoted to biomedical language processing.


9:00-9:15 Greeting

Biomedical Name Recognition

9:15-9:45 Jun'ichi Kazama, Takaki Makino, Yoshihiro Ohta, Jun'ichi Tsujii. Tuning support vector machines for biomedical named entity recognition
9:45-10:15 Lorraine Tanabe, W. John Wilbur. Tagging gene and protein names in full text articles
10:15-10:45 K. Bretonnel Cohen, Andrew E. Dolbey, George K. Acquaah-Mensah, Lawrence Hunter. Contrast and variability in gene names

10:45-11:00 Break

Machine Learning of Biomedical Language

11:00-11:30 Pierre Zweigenbaum, Natalia Grabar. Accenting unknown words in a specialized language
11:30-12:00 Lee Christensen, Peter Haug, Marcelo Fiszman. MPLUS: a probabilistic medical language understanding system
12:00-12:30 David Campbell, Stephen Johnson. A transformational-based learner for dependency grammars in discharge summaries.

12:30-2:00 Lunch

Biomedical Indexing

2:00-2:30 Gail Sinclair, Bonnie Webber, Duncan Davidson. Enhanced natural language access to anatomically-indexed data
2:30-3:00 Olivier Bodenreider, Thomas Rindflesch, Anita Burgun. Unsupervised, corpus-based method for extending a biomedical terminology
3:00-3:30 Stefan Schultz, Martin Honeck, Udo Hahn. Biomedical text retrieval in languages with a complex morphology

3:30-3:45 Break

Biomedical Information Resources

3:45-4:15 Eneida Mendonca, Stephen Johnson, Yoon-ho Seol, James Cimino. Analyzing the Semantics of patient data to rank records of literature retrieval
4:15-4:45 G. Demetriou, R. Gaizauskas. Utilizing text mining results: The Pasta Web System
4:45-5:15 James Pustejovsky, Jose Castano, Jason Zhang, Roser Sauri, Wei Luo. Medstract: creating large-scale information servers from biomedical texts


Stephen Johnson (Columbia University), chair AMIA NLP-SIG
Udo Hahn (Freiburg University, Germany)
Judith Klavans (Columbia University)

Program Committee