Second CALBC Workshop – 16/17/18 March 2011 – EBI, Hinxton

Day 1

Time Day 1 (Wednesday – March 16th, 2011)
12.00-13.00 Lunch
13.00-15.00 Session 1: Introduction to the CALBC challenges, setup, participation
13.00-13.15 Overview: Setup of the first and the second CALBC challenge, overview on the analyses (D. Rebholz-Schuhmann, EBI, U.K.) (pdf)
13.15-13.45 Methods for Matching of Annotations, Harmonisation and Evaluation (Jan Kors, Erasmus University Medical Center, Rotterdam, Nl) (pdf)
13.45-14.10 Concept identification by machine learning aided dictionary-based named entity recognition and rule-based entity normalisation (György Móra, University of Szeged, Hu) (pdf)
14.10-14.35 Annotating the CALBC corpus with a machine learning harmonization approach (David Campos, Universidade de Aveiro, Pt) (pdf)
14.35-15.00 Annotating large corpora with concept retrieval (Rafael Berlanga1, Universitat Jaume I, Es) (pdf)
15.00-15.30 Break
15.30-17.00 Session 2, part 1: Annotation methods applied to the CALBC corpus
15.30-15.55 Dictionary-based concept identification with UMLS (Max De Wilde, University of Antwerp, Be) (pdf)
15.55-16.20 OntoGene at CALBC II and Some Thoughts on the Need of Document-Wide Harmonization (Simon Clematide, University of Zurich, Ch) (pdf)
16.20-16.50 Challenge I vs. Challenge II: Set-up, Participation Data and Feedback(Udo Hahn, Friedrich-Schiller-University, Jena, De; D. Rebholz-Schuhmann) (pdf)
16.50-17.00 Recap and initial open discussion on the setup and outcome of the CALBC project and challenge (pdf)
17.00-18.00 Keynote talk: Prof. Yves Moreau (Katholieke Universiteit, Leuven, Be)
Candidate gene prioritization by genomic data fusion
18.00 Bus ride to Cambridge
19:00 Dinner, Queens College, Cambridge

Day 2

Time Day 2 (Thursday - March 17th, 2011
8:30-9:00 Morning Coffee
9.00-11.30 Session 2, part 2: CALBC II challenge and gold standard data
9.00-9.30 Building the SSC and evaluation of the annotation systems against the SSC (I. Lewin, EBI, U.K.; J. Kors; D. Rebholz-Schuhmann) (pdf)
9.30-10.00 Evaluation of the SSC against the gold standard corpora (Senay Kafkas, EBI, U.K.; Dietrich Rebholz-Schuhmann) (pdf)
10.00-10.30 A CRF-based approach to harmonize heterogeneous gene/protein annotations (David Campos, Universidade de Aveiro, Pt) (pdf)
10.30-11.00 Use cases for improvements of annotation solutions based on the SSC (David Milward, Linguamatics, Cambridge, U.K.; Jan Kors; Erik van Mullighen) (pdf)
11:00-11:30 Coffee Break
11.30-12.30 Keynote Talk: Lynette Hirshman (Mitre, U.S.A.)
Coupling Evaluation to End Users: Case Studies in Text Mining for Biomedicine
12:30-13:30 Lunch time
13.30-15.30 Session 3:Normalisation of data and Semantic Web
13.30-14.00 Normalisation of lexical entities: Jochem, LexEBI, cross-comparisons (D. Rebholz-Schuhmann et. al) (pdf)
14.00-14:30 Normalisation of the silver standard corpus using normalised lexical resources: evaluation of annotation solutions (Ernesto J. Ruiz , Oxford University, U.K.; Ian Lewin) (pdf)
14.30-15.00 A Semantic Model for Federated Queries Over a Normalized Corpus (Samuel Croset, EBI, U.K.; C. Grabmüller, EBI, U.K.) (pdf)
15.00-15.30 Integration of literature with biomedical data resources- the SESL project (Christoph Grabmüller, EBI, U.K.; Samuel Croset, EBI, U.K.; Dietrich Rebholz-Schuhmann)
15:30-16:00 Break
16.00-17.00 Keynote Talk: Therese Vachon (Novartis Institutes for Biomedical Research, Basel, Ch)
17.00-18.00 Poster Session

Day 3

Time Day 3 (Friday- March 18th, 2011)
8:30-9:00 Morning Coffee
9.00-10.00 Keynote talk: Timo Hannay (Digital Science / Nature Publishing Group, London)
When content meets technology
10.00-12.30 Session 5: Large-scale annotation – next generation?
10.00-10.20 Is the interoperability and normalisation of semantic resources solved?
10.20-10.40 Is the integration of different semantic types in the same corpus solved?
10.40-11.00 Which use cases from involving Semantic Web technology would profit from the integration of the scientific literature?
11:00-11:30 Coffee Break
11.30-11.50 Does the CALBC approach scale in such a way that all scientific publications in the biomedical domain would be annotated with automatic means in the future?
11.50-12.10 Can we tackle the problem of multi-linguality with the CALBC approach?
12.10-12.30 What other data resources apart from the scientific biomedical literature should be annotated with the CALBC approach?
12.30-13.00 Wind-up and closing
13:00 Lunch time