Biological Event Extraction

This project concerns the extraction from text of biomolecular events, which are recursively nested, typed associations of arbitrarily many participants (genes / gene products) in specific roles.

Software

The Turku Event Extraction System (TEES) was used by the Turku BioNLP group's entry in the BioNLP'09 Shared Task, in which it was the best performing system. It has been distributed under GPL.

EVEX dataset

Our system has been applied to all abstracts in PubMed. The resulting data is released in several data formats (plain text, XML, MySQL) and contains supporting analyses such as all syntactic parses.