A combining approach to find all taxon names (FAT)

Abstract

Abstract.-Most of the literature on natural history is hidden in millions of pages stacked up in our libraries. Various initiatives aim now at making these publications digitally accessible and searchable, applying xmlmark up technologies. The unique biological names play a crucial role to link content related to a particular taxon. Thus discovering and marking them up is extremely important. Since their manual extraction and markup is cumbersome and time-intensive, it needs be automated. In this paper, we present computational linguistics techniques and evaluate how they can help to extract taxonomic names automatically. We build on an existing approach for extraction of such names (Koning et al. 2005) and combine it with several other learning techniques. We apply them to the texts sequentially so that each technique can use the results from the preceding ones. In particular, we use structural rules, dynamic lexica with fuzzy lookups, and word-level language recognition. We use legacy documents from different sources and times as test bed for our evaluation. The experimental results for our combining approach (FAT) show greater than 99% precision and recall. They reveal the potential of computational linguistics techniques towards an automated markup of biosystematics publications.

The big questions for biodiversity informatics

“…GBIF, REMIB, VertNet, SpeciesLink; Graham et al, 2004;Stein & Wieczorek, 2004;Guralnick & Hill, 2009). In parallel, major effort has been invested in compiling digital taxonomic name resources and the taxonomic literature (Koning et al, 2005;Sautter et al, 2006). Finally, display and visualization efforts include presenting compiled data on maps, or creating information pages with biodiversity data 'mashed up' with other types of data (Butler, 2006;Janies et al, 2007).…”

Semantic annotation of biosystematics literature without training examples

“…An example of a rule-based annotation system is GoldenGATE (Sautter et al, 2006), which is a specialized XML editor for biosystematics literature. GoldenGATE allows the user to invoke different built-in functions to paginate documents, tag taxonomic names, and tag paragraphs.…”

Unsupervised semantic markup of literature for biodiversity digital libraries

“…The majority of study on structuring taxonomic descriptions focuses on the paragraphs with limited semantic relationships, such as taxon names and/or ranks [3,4,6]. Research focusing on semantic-rich sections, such as morphological description sections, took one of the three approaches: the syntactic parsing approach, the rule-based approach, or the machine learning approach.…”