Submitted for publication Learning Information Extractors for Proteins and their Interactions

We present results from a variety of learned information extraction systems for identify-ing human protein names in Medline ab-stracts and subsequently extracting interac-tions between the proteins. We demonstrate that machine learning approaches using sup-port vector machines and hidden Markov models are able to identify human proteins with higher accuracy than several previous approaches. We also demonstrate that vari-ous rule induction methods are able to iden-tify protein interactionsmore accurately than manually-developed rules. 1