Names discovery and fuzzy matching

Location: Marine Biological Laboratory, Woods Hole, Massachusetts

Date: Wednesday May 27 to Thursday May 28

Travel Logistics: Logistics - to, from, and in Woods Hole

Agenda: Nomina IV Agenda

Nomina IV is intended to be a technical workshop focused on the development of computer algorithms for identifying scientific names within text documents (Taxonomic Name Recognition (TNR)) and algorithms that link variant spellings of scientific names together (Fuzzy Name-Matching). These critical names discovery/integration tools are required for automated indexing sources of biological information.  Indeed, this meeting has been prompted by requests from the Biodiversity Heritage Library to improve names discovery within that corpus of digital literature. A variety of such tools already exist (examples being FAT, TAXAMATCH, TaxonFinder, FindIT).  Our goal is to:

• review the current state of these two areas where a number of tools and services are available
• identify use cases for these technologies and ensure requirements stemming from them are met
• produce a widely accessible roadmap that will coordinate development