Text Mining in the Life Sciences

October 13th, 2005

Schloss Birlinghoven, Sankt Augustin, Germany

 Picture gallery

Introduction

Text Mining has come of age. Still an innovative technology, the recent years have seen a growing tendency to apply Text Mining systems in data intensive industries such as the life sciences. Technological advances on the one hand and the pressure to consider available textual information in complex decision-making processes on the other hand result in the increasing demand for methodological and algorithmic support in analysing this information.

The 3rd Symposium Text Mining in the Life Sciences, jointly organised by the Fraunhofer Institute SCAI and TEMIS SA, aims to provide an overview of current trends and challenges in putting Text Mining approaches to work in a variety of scenarios. More and more these methods are used to address tasks in contexts such as patent analysis, competitive intelligence or knowledge management. With the inherent limitations of traditional full-text search becoming more apparent, the trend goes towards systems that know how to recognise and handle objects as well as their relationships, thus allowing the users to retrieve, manipulate and analyse specific facts and topics instead of just entire documents.

This year’s presentations underline this development with insights from the perspective of industrial users as well as academic and corporate Text Mining experts. This programme as well as the scenic setting of the Symposium in Schloss Birlinghoven provides the framework for a day of fruitful and intensive exchange between experts working in the field.

Organization

 TEMIS SA
 Fraunhofer SCAI

Speaker

9:00 – 9:15
Martin Hofmann
Head of the Department of Bioinformatics,
Fraunhofer Institute for Algorithms and Scientific Computing (SCAI)
Opening address

9:15 – 9:55
Udo Hahn
Dept. Computer Linguistics, University of Jena
Evaluating the Performance of Text Mining Systems in the Biology Domain

9:55 – 10:35
Barrou Diallo
European Patent Office R&D, Den Haag
Perspectives and challenges for the large scale analysis of patent documents

10:35 – 11:00
Break & demos

11:00 – 11:40
Mathieu Plantefol
TEMIS
The BER-module for protein interactions - quality assessment

11:40 – 12:20
Joël Crouzet
INSERM Transfert, Paris
Text Mining at the INSERM

12:20 – 13:20
Lunch

13:20 – 14:00
Günther Kurapkat (TEMIS) and Helmut Grotz (MDL)
Text Mining and Chemistry

14:00 – 14:40
Marc Zimmermann
Fraunhofer Institute SCAI
Information extraction from chemical images

14:40 – 15:10
break & demos

15:10 – 15:50
Frederique Lisacek
GeneBio, Geneva
Detection of technology shifts in scientific and patent literature

15:50 – 16:30
Jean Delahousse
Mondeca Paris, France
Ontologies and Text Mining in the Life Sciences

16:30 – 17:00
Final discussion

Registration

Please register before 6th October 2005 with:

Gisela-Renate Thies
Fraunhofer-Institute SCAI
Schloss Birlinghoven
53754 Sankt Augustin

Phone: +49 (0) 2241-14 2769
Fax: +49 (0) 2241-14 2102
 Gisela-Renate.Thies(at)scai.fraunhofer.de