Scientific Discourse Meeting, January 30, 2012
Domeo Annotation Toolkit and text mining
Creating, visualising, sharing, curating and discussing text mining results with Domeo Annotation Toolkit, Apache UIMA and Apache Clerezza.
Biomedical research has experienced an explosion of results in the literature over several decades. There is a continuously accelerating increase in number of publications, and continuing pressure to read faster and publish more. This poses problems of tractability of the literature to the individual researcher as well as to database curators and ontologists. Biomedical textmining has a great potential to help resolve these problems. It is a diverse and active research effort conducted across hundreds of research groups and projects, funded from many sources.
The Domeo Web Annotation Toolkit provides several important items of common infrastructure that can help support the textmining community.
- Shared results repository with selective sharing (personal, group, public)
- Standardized serialization and export of results in Annotation Ontology RDF/XML
- Results injection and contextualization on any web page
- Common curation, annotation and comparison user interface
- Web service interfaces
This talk will present
- current facilities and future plans for the Domeo Annotation Toolkit relating specifically to textmining use cases.
- and details of the integration of the Domeo Annotation Toolkit with Apache UIMA through Apache Clerezza.
Dial-in & IRC Information:
- Time: 10:00 EDT
- Dial-In #: +1.617.761.6200 (Cambridge, MA)
- Dial-In #: +18.104.22.168.79.03 (Paris, France)
- Dial-In #: +44.203.318.0479 (London, UK)
- Participant Access Code: 42572 ("HCLS2")
- IRC Channel: irc.w3.org port 6665 channel #HCLS2 use IRC direct link or (see W3C IRC page for details, or see Web IRC)
- Mibbit quick start: Click on mibbit for instant IRC access
- Duration: 1hr