TRAINING ›

Text Mining

Venue: 
European Bioinformatics Institute, Cambridge, CB10 1SD
United Kingdom
See map: Google Maps
Date: 
Wednesday, April 21, 2010 - Thursday, April 22, 2010
Organizers: 
Dietrich Rebholz-Schuhmann , EMBL-EBI
Admin support: 
Alison Barker , EMBL-EBI, UK
Participation: 
Open application with selection
Overview | Programme | Registration | Trainers | Speakers | Venue | Contacts

Overview

 

The purpose of this event is to teach basic techniques in information retrieval (IR) and information extraction (IE) in the biomedical domain and to give hands-on training on existing solutions.

Objectives

 

  • Learn how to use existing text mining solutions
  • Understand basic text mining techniques and get an overview of underlying technologies
  • Appreciate the variety of text mining components and the contexts in which they are used individually and in combination
  • Interact with text miners to express needs for future developments

Programme

 

Wednesday 21st April 2010

09.00 -10.30
Feature extraction from biomedical text for data integration
(D. Rebholz-Schuhmann)
The starter kit:Extraction of tokens, terms and named entities, from documents to profiles, similarity measures, language models,use in biomedical text mining
10.30-11.00
Coffee break
11.00-12.30
Natural language processing(Ian Lewin)
Syntactical structure of sentences, parsing techniques, relation extraction.This presentation gives insights on the use of grammars and syntactical analyses to filter out explicit relations and other information from the literature.
12.30-13.30
Lunch
13.30 -15.00
Access to literature for biologists and bioinformaticians
(D. Rebholz-Schuhmann)
Presentation and explanations to EBI's Literature Services: CiteXplore, EbiMed, MedEvi, Whatizit.
15.00-15.30
Coffee break
15.30-17.00
Text Mining in Biomedicine (Prof. Sophia Ananiadou, NaCTeM)
NaCTeM is providing TM services to the public: KLEIO, FACTA, MEDIE,TerMine,Acromine. The solutions will be presented and explained.--> Information extraction using UIMA and a biomedical type system
(Prof. Udo Hahn, University of Jena)
UIMA is a Java-based software package that contains a number of text mining solutions.Tokens and entities are linked to a semantic type and advanced parsing methods can be applied to the identified entities. The part of the workshop gives insights into the usage of UIMA .
17.00-18.00
Discussion
Time for questions, expectations for the future

Thursday 22nd April 2010

09.00 -10.30
Use of ontological resources for Text Mining:
(D.Rebholz-Schuhmann)
Exploitation of biomedical semantic resources: overview of resources, biolexicon, bio-ontologies. Use of ontological resources for information extraction.
10.30-11.00
Coffee break
11.00-12.30
Success stories in biomedical text mining
(D. Rebholz-Schuhmann)
Use of the programmatic text mining infrastructure at the EBI: calling text mining services.Text mining solutions for bioinformaticians and biomedical challenges. Examples of knowledge discovery through text mining. Overview into ongoing work and future developments.
12.30-13.30
Lunch

Registration

 

Registration Closed

Tags:
bioinformatics