An essential part of bioinformatic research concerns the iterative process of validitating hypotheses by analysing facts stored in databases and in published literature. This process can be enhanced by language technology methods, in particular by automatic in-depth text understanding.
A high-quality system for extracting relevant information from biological texts must include an algorithm for distinguishing between the background and the foreground information in a text, in order not to confuse the previous research referred to and the current research reported in a particular paper.
Furthermore, text understanding requires a strategy for anaphora recognition. The paper focuses on these two issues in automatic processing of abstracts in the domain of genetics
på CD-rom