In this talk I will describe text mining activities conducted by the OntoGene/BioMeXT research group (http://www.ontogene.org/) at the Institute of Computational Linguistics of the University of Zurich The goal of the group is to perform large-scale information extraction from textual sources for life sciences applications.

The OntoGene text mining system is based on a scalable entity recognition component, an in-house dependency parser, and a flexible relation mining approach. The OntoGene team has participated in several community-organized biomedical text mining challenge (BioCreative, BioNLP, CALBC), obtaining competitive results in several of them.

I will present examples from projects dealing with knowledge extraction from the scientific literature, identification of possible causes of psychological disorders, epidemiological applications in veterinary medicine, author disambiguation, and assisted curation for life science databases.

Fabio Rinaldi is the leader of the OntoGene/BioMeXT research group, based at the University of Zurich, and a member of the Swiss Institute of Bioinformatics. The main focus of his research is on text mining technologies for the extraction of information from biomedical text. He is author or co-author of 100+ scientific publications dealing with topics such as Ontologies, Text Mining, Text Classification, Document and Knowledge Management, Language Resources and Terminology.