2nd CALBC Workshop
Location: European Bioinformatics Institute, Hinxton, Cambridge, U.K. [Map]
Date: 16/17/18 March 2011
Part 1: 16/17 March 2011 (50 GBP incl. workshop dinner)
The workshop will cover the following topics:
- Session 1: Introduction to the CALBC challenge I and II, setup of the CALBC challenge II, participation to the challenge, obstacles and lessons learnt
- Part 1: Annotation methods applied to the CALBC corpus (incl. presentations by participants), performances against the Silver Standard Corpus
- Part 2: Comparisons between the silver standard corpus and the gold standard corpora, exploitation of the silver standard corpus for machine learning approaches and improved text mining solutions
- Session 3: Normalisation of named entities in terminological resources and in the silver standard corpus, use of the normalised representation in the Semantic Web, obstacles and benefits
- Session 4: Poster Session and wrap-up
Part 2: 18 March 2011 (no charge), "Large-scale annotation - next generation"
In the CALBC project the project partners have approached a number of problems that in principle lead to better support of the automatic annotation of the scientific literature. First, the project partners have harmonised annotations from different solutions. Second, they have generated a corpus that contains a large number of annotated semantic types. Third, they have finalized performance measurements to assess the quality of the Silver Standard Corpus against the Gold Standard corpora. Last, they have generated a semantic resource that enables exploitation of the annotated corpus as part of the public Semantic Web infrastructure.
During this part of the workshop the participants will have the opportunity to discuss a number of innovative questions. For example:
- 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?
- Is the integration of different semantic types in the same corpus solved?
- Which use cases from involving Semantic Web technology would profit from the integration of the scientific literature?
- Can we tackle the problem of multi-linguality with the CALBC approach?
- What other data resources apart from the scientific biomedical literature should be annotated with the CALBC approach?
- Interoperability and normalisation of semantic resources
Detailed workshop program