BioCreative & BeCalm
We are happy to announce that we will host BioCreative Workshop 2016 at Corvallis Oregon, USA on August 1-2, 2016, satellite to the International Conference on Biological Ontology (ICBO) 2016. The goal of this workshop is to provide a discussion forum for topics of interest to the BioCreative community and to encourage synergistic interactions with the ontology community. BioCreative workshop 2016 second day session will run jointly with the ICBO meeting.
The BioCreative V.5 Challenge will address:
- the development and evaluation of named entity recognition systems for chemical and gene/protein entity mentions and
- the proof-of concept implementation of a continuous text annotation metaservice, called BeCalm.
Results of the BioCreative V.5. BeCalm. challenges will be presented in an evaluation workshop and proceedings papers, similar to previous BioCreative events (see http://www.biocreative.org/resources/biocreative-v/proceedings-biocreative5).Additionally a special issue devoted to BioCreative V.5. will cover the results and participation at this task. Participating annotation servers teams will be invited to join BeCalm. metaserver overview paper.
BioCreative V.5. BeCalm tasks
In order to enable a more robust evaluation setting that facilitates direct comparison and visualization of different online and offline predictions the BeCalm. (Biomedical Annotation Metaserver) platform will be used (Sign in here). Following the impact and success of previous BioCreative-related initiatives, text mining and language processing researchers world-wide will be invited to implement text Annotation Servers and to provide their results for the following tasks.
The Biocreative metaserver challenge will address:
- CEMP (Chemical Entity Mention recognition). This tasks requires the recognition of chemical named entity mentions in text. This implies to return the start and end indices corresponding to all the chemical entity mentions.
- GPRO (Gene and Protein Related Object recognition). For this task teams have to recognize mentions of gene and protein related objects (named as GPROs) in running text.
- TIPS (Technical interoperability and performance of annotation servers). (Technical interoperability of named entity recognition). This task will focus on the technical aspects of the evaluation of continuous text Annotation Servers (ASs) for named entity recognition. This is an open task, in the sense that it is not restricted to a particular named entity recognition task. Moreover, the Annotation Servers may be fully developed in-house or integrate third party recognition software as building block components (see list of initial existing candidate bio-NER tools). AS will consist of a "REST" (Representational State Transfer) API application that responds to the request by returning NER annotation results as structured data (represented in particular formats XML/BioC, JSON and TXT, see http://www.becalm.eu/api )
Teams should participate in at least one task. Participation in all tasks, and in particular offline and online competitions, are most welcomed.
In line with previous BioCreative challenges, the result of participating teams will be presented at the BioCreative V.5. evaluation workshop that will take place in Madrid (Spain) in March 2017.