BOOTSTREP PROJECT

In this project, we will employ various techniques to address the following issues:

• Automatically acquire new terms and concepts from literature;
• Cluster and classify biological terms;
• Automatically extract linguistics properties of biological terms;
• Automatically create, maintain and update biological facts repository;
• Access the biological factual information via multilingual query interface (for English, German, Italian and French).

We foresee that our project will help develop an environment that bridges work on heterogeneous forms of biological terminologies, lexicons, ontologies and fact databases, which will be a major step towards increased semantic interoperability for all actors involved in the biology domain, such as scientists, clinicians, bio tech industry and business.

Our projects partners include:

• The Jena University Language & Information Engineering Lab (Germany),
• European Molecular Biology Institute / European Biology Informatics (UK),
• Consiglio Nazionale delle Ricerche � Istituto di Linguistica Computazionale (Italy),
• Universit� de Rennes (France),
• Institute for Infocomm Research (Singapore), and
• Universit�tsklinikum Freiburg (Germany).

We are based in the MIB (Manchester Interdisciplinary Biocentre) Building where NaCTeM (NAtional Centre of TExt Mining) is located.