Seminar — Walter Daelemans

The Biograph project aims at developing a new methodology for text mining from heterogeneous information sources. The final goal of the project is to show new results in mining for previously unknown relations between genes and phenotypes, and improved gene prioritisation finding non-obvious disease causing genes. It is a multidisciplinary project within the University of Antwerp carried out by three research groups: a text mining group (CLiPS), a molecular genetics group (AMG), and a data mining group (ADReM).

I will describe the project as a whole and go into some detail about work in progress within CLiPS on the text mining aspects of the project: unsupervised and supervised relation finding, and the modeling of negation and modality (hedge) and their scope for incorporation into the datamining step.