Satellite meeting for Literature and Text mining related issues

Topics

Different web tools allow researchers to search literature databases and integrate semantic information extracted from text with external databases and ontologies. Some of them even provide accessible APIs so users can build their own text mining pipelines.

Enhanced literature search and retrieval engines

 http://www.knewco.com/

 http://www.gopubmed.com/

 http://www.novoseek.com/

 http://www.ihop-net.org/UniPub/iHOP/

 http://www.ebi.ac.uk/citexplore/

 EBI text mining tools

Text mining web services

 BioAID workflows

 iHOP webservices

 Whatizit

 http://www.biosemantics.org

 http://nactem.ac.uk/

TM related web services provided by  DBCLS

•  Allie
•  OReFiL

Assessment of text mining tools (both engines and web services)

 BioCreative MetaServer Platform ( talk from Florian Leitner about the system)

 XML-RPC interface of BCMS

ieXML: how to standardize the annotation of named entities

 http://www.ebi.ac.uk/Rebholz-srv/IeXML/

Other stuff

 http://www.ebi.ac.uk/Rebholz/resources.html

 http://ex.perimental.net/scaiview/ (This shows the front-end of a text-mining system I (Tobias) developed previously. It has overlapped tagging as a result of multi-class NER and fulltext search)

The questions that this satellite meeting could try to answer are:

For developers:

• What are the missing elements for better integration of the different services?

• Which are the best formats for information extraction data exchange (ieXML, RDF)?

• Which components of the text minig architecture can be moved from to the server to the client (AJAX, browser plugins)?

• Is it possible to build portable text mining systems? Can systems be adapted to specific domains and specific tasks without the assistance of an experienced language processing specialist?

• How can we cope with full text data (format / copyright)?

For users:

• What is the actual utility of text mining in the workflows of the various communities of potential users—model organism database curators, bedside clinicians, biologists utilizing high-throughput experimental assays, hospital billing departments?

• How usable are biomedical text mining applications? How does the application fit into the workflow of a complex bioinformatics pipeline? What kind of training does a bioscientist require to be able to use an application?

• How robust and reliable are biomedical text mining applications?

Chairperson

•  Alberto Labarga ( EBI,  Dasty,  Elsevier Grand Challenge, Univ. of Granada, Spain)

Targets

• Developers of literature and text mining related software and services
• End-users of these services

Attendees

• Yulia Kovarskaya
• Hong-Woo Chun
• Yasunori Yamamoto
• Tobias Gattermayer
• José María Fernández
• Pierre Lindenbaum
• Atsuko Yamaguchi

Date

• 2009/3/17 13:00-17:00

Room

• Seminar Room (1F)

Presentations

review of text mining systems related to life sciences

View more presentations from Alberto Labarga.

Notes

Results

We need to retake this since the schedule was a little fuzzy today ;-)

• We did an exploration of existing services (see presentation above)
• We explored the use of scifoaf (Pierre Lindenbaum) -> We need unique IDs for authors in publications!
• We implemented some clients for  XML-RPC interface of BCMS and  iHOP webservices

TODOs

• check  ieXML service at EBI is it valid? can we generate XSLT for this?
• check  http://u-compare.org/