Learning to Extract Genic Interactions Using Gleaner

We explore here the application of Gleaner, an Inductive Logic Programming approach to learning in highly-skewed domains, to the Learning Language in Logic 2005 biomedical information-extraction challenge task. We create and describe a large number of background knowledge predicates suited for this task. We find that Gleaner outperforms standard Aleph theories with respect to recall and that additional linguistic background knowledge improves recall.