An evaluation of taxonomic name finding & next steps in Biodiversity Heritage Library (BHL) developments

Abstract

The Biodiversity Heritage Library (BHL) is an international consortium of natural history libraries that are actively scanning scientific literature from their collections and publishing the digitized content online at http://www.biodiversitylibrary.org. The presentation will cover updates on BHL progress thus far, including a review of the BHL portal application and services developed for bibliographic data exchange, as well as a roadmap of features scheduled for design and development. Of interest to taxonomists and bioinformaticians, the presentation will also cover a recently completed evaluation of taxonomic name finding algorithms, including TaxonFinder and FAT. Discussion will include a review of successes and failures in extracting taxonomic name strings from the BHL corpus, as well as suggestions for improvement.