1st CALBC Workshop

Location: European Bioinformatics Institute, Hinxton, Cambridge, U.K. [Map]

Date: 17/18 June 2010

At the CALBC workshop, participants discussed the outcome of the challenge. The CALBC project partner explained in detail previous work on the corpus and presented the results from the challenge. Also, participants presented their work to meet the demands of the challenge.

Proceedings

A collection of abstracts and detailed workshop information are available in the workshop proceeding. If you are willing to know more about this event, please click here to download the proceeding.

Agenda of the workshop

Day 1: 17 June 2010, 11h00 – 18h00

Session 1: Introduction, preparation and outcome of CALBC Challenge I,11h00-13h00

11.00-11.30	“Welcome and Introduction” (Dietrich Rebholz-Schuhmann) [Slides] purpose of the CALBC project, timelines and overview
11.30-12.00	“Pilot project and Silver Standard Corpus I (SSC I)” (Erik van Mulligan) [Slides] development of SSC I: harmonisation and evaluation procedures, quality of the SSC I
12.00-12.30	“CALBC Challenge I” (Dietrich Rebholz-Schuhmann) [Slides] Presentation and Discussion of CALBC challenge I and its outcome
12.30-13.00	“Relevance of the SSC I and SSC II” (David Milward) [Slides] Comparison to other challenges, open discussion
13.00-14.00	Lunch time: Opening of the poster session

Session 2: Annotation methods, part I,14h00 – 15h30

14.00-14.30	“Robust Biomedical Entity Recognition Using Optimal Feature Set”(Faisal Mahbub Chowdhury) [Slides]
14.30-15.00	“A system to identify bio-entities using Conditional Random Fields”(Qi Wei) [Slides]
15.00-15.30	“Solution not based on training data” (Rafael Berlanga) [Slides]
15:30-16.00	Break

Session 3: Silver Standard Corpora,16h00 – 18h00

16.00-16.30	“The Silver Standard Corpus vs. gold standard corpus”(Udo Hahn, Dietrich Rebholz-Schuhmann) [Slides]
16.30-17.00	“Towards configurable Silver Standard Corpora”(Udo Hahn) [Slides]
17.00-18.00	Keynote talk:Yves Lussier, MD, University of Chicago (Udo Hahn) [Slides] “Quantized phenotypes emerge as multiscale mechanisms underpinning complex traits from mining genetic narratives, ontologies, and RNA sequences” The keynote talk is concerned with the exploitation of the scientific literature for biomedical knowledge discovery. Yves Lussier has exploited terminological and semantic resources to identify phenotypic information from the literature and to link molecular biology to clinical medicine. Yves is member of the scientific advisory committee of the CALBC challenge.
Dinner at Jesus College, Cambridge

Day 2: 18 June 2010, 9h00 – 16h00

Session 4: Annotation methods, part II,9h00-11h00

9.00-9.30	“OntoGene in CALBC” (Fabio Rinaldi)
9.30-10.00	“Towards automatic biomedical entity annotation with reduction of error propagation” (Kazuo Hara) [Slides]
10.00-10.15	“Annotation of the CALBC corpus using biomedical terminological resources (Whatizit)” (Dietrich Rebholz-Schuhmann) [Slides]
10.15-10.30	“Annotating the CALBC SSC I Corpus Using the JULIE Lab Tools” (Udo Hahn) [Slides]
10.30-10.45	“Annotating the CALBC corpus with Peregrine” (Erik van Mulligan)
10.45-11.00	“Annotating Biomedical Entities with I2E using Multiple Ontologies” (David Milward)

Session 5: Preparation of the next challenge,11h00-13h00

11.00-11.15	“CALBC Opinion Poll” (Udo Hahn, Katrin Tomanek) [Slides]
11.15-13.00	Discussion: “Conduct of the future CALBC challenge round”(Udo Hahn)
13.00-14.00	Lunch time

Session 6: Exploitation of the SSC for the Semantic Web,14hr00-16hr00

14:00-15.00	Keynote talk: “Information Extraction - The Missing Link in Linked Data?” (M. Scott Marshall, PhD, Leiden University Medical Center Biomedical Data integration in the Semantic Web)
15.00-16.00	Open Discussion: “CALBC, Literature and Semantic Web: Quo Vadis”(Dietrich Rebholz-Schuhmann) [Slides] If we can transform literature into a representation that is suitable for the Semantic Web, what requirements have to be fulfilled and how this resource can be exploited in the future?