Funded Projects

  • Contextual Text Mining from the Biomedical Scientific Literature
    • European Commission, FP7 Marie Curie International Reintegration Grant, Principal Investigator, 2012-2016.
    • Summary: Scientific publications are the main media through which researchers report their new findings. The huge amount and the continuing rapid growth of the number of published articles in biomedicine, has made it particularly difficult for researchers to access and utilize the knowledge contained in them. Developing text mining techniques to automatically extract biologically important information such as relationships between biomolecules is not only useful, but also necessary to facilitate biomedical research and to speed-up scientific progress. For the extracted information to make sense, a great deal of biological context such as relationship type and experimental method are required. The goal of the proposed project is to design methods based on natural language processing and machine learning to extract relationships among biomolecules and their context information.
  • Jointly Self-trained Parsers
    • Bogazici University Research Fund, BAP, Principal Investigator, 2012-2013.
    • Summary: Determining the syntactic structure of a sentence is a fundamental step towards understanding what is conveyed in that sentence. While statistical approaches reach their highs in supervised settings, semi-supervised approaches like self-training of parsers is starting to emerge as a next challenge. Such parsers train on their own outputs with the goal of achieving better results by learning on their own. However, only a small number of self-trained parsers have met this goal so far. In this project, we will tackle the problem of self-training a feature-rich discriminative constituency parser.