BioASQ Challenges on Biomedical Information Retrieval and Question Answering

Every day, approximately 3000 new articles are published in biomedical journals. That averages to more than 2 articles every minute. Managing this large amount of data is a challenge in itself. Yet, ensuring that this wealth of knowledge is used for the sake of the patients in a timely manner is an even more demanding task for both computer scientists and biomedical experts.

The BioASQ project, which started on October 1st 2012 and runs for 2 years, aims to push research in information technology towards highly precise biomedical information retrieval systems. The project will achieve this goal through a competition (challenge), in which systems from teams around the world will compete. BioASQ will provide the data, software, hardware and the evaluation infrastructure for the challenge. By these means, the project will ensure that the biomedical experts of the future can rely on software tools to identify, process and present the fragments of the huge space of biomedical resources that address their personal questions.

The tasks included in the BioASQ challenges will help advance the state of the art in two fields. First, the automatic classification of biomedical documents will be improved. Here, systems will be required to tag large numbers of scientific biomedical articles with terms from a predefined biomedical vocabulary. Additionally, the challenge will evaluate how well systems identify text fragments in scientific articles, and related data in public knowledge bases, in order to answer questions set by the European biomedical expert team of BioASQ.

Further results of the project will include a set of open-source tools and a social network that will support experts in setting up similar challenges, beyond the end of the project.

The BioASQ team combines researchers with complementary expertise from 6 organisations in 3 countries: the Greek National Center for Scientific Research "Demokritos" (coordinator), participating with its Institutes of "Informatics & Telecommunications" and "Biosciences & Applications", the German IT company Transinsight GmbH, the French University Joseph Fourier, the German research Group for Agile Knowledge Engineering and Semantic Web at the University of Leipzig, the French University Pierre et Marie Curie-Paris 6 and the Research Center of the Athens University of Economics and Business in Greece. Moreover, biomedical experts from several countries assist in the creation of the evaluation data and a number of key players in the industry and academia from around the world participate in the advisory board of the project.

For further information, please visit:
http://www.bioasq.org

ABOUT Transinsight GmbH

Transinsight develops semantic software products in the field of bioinformatics and geophysics. Developments in bioinformatics include text mining and analysis of biological high-throughput data. Their semantic software platform Enterprise Semantic Intelligence® powers the knowledge-based search systems www.Go3R.org and www.GoPubMed.com, semantic search engines for the next generation. In the area of geophysics the product IGMAS+ is a high performance tool for the Full Tensor Gravity (FTG) Modeling (see also www.PotentialGS.com). In acknowledgement of the technologies developed by the company, Transinsight has repeatedly been honoured with national and international awards. The firm works in close collaboration with the Dresden University of Technology. Selected customers are: Unilever, BASF, BfR, Statoil, RWE, Abcam and EMBL.

Transinsight GmbH
Tatzberg 47-51
D – 01307 Dresden
Germany

+49 351 796 57 80
www.transinsight.com

This release was published on openPR.