Bernd Müller, Roman Klinger, Harsha Gurulingappa, Heinz-Theodor Mevissen, Martin Hofmann-Apitius, Juliane Fluck and Christoph Friedrich

Abstract

In information retrieval, named entity recognition gives the opportunity to apply semantic search in domain specific corpora. Recently, more full text patents and journal articles became freely available. As the information distribution amongst the different sections is unknown, an analysis of the diversity is of interest. This paper discovers the density and variety of relevant life science terminologies in Medline abstracts, PubMedCentral journal articles and patents from the TREC Chemistry Track. For this purpose named entity recognition for various bio, pharmaceutical, and chemical entity classes has been conducted and the frequencies and distributions in the different text zones analyzed.
The full texts from PubMedCentral comprise information to a greater extent than their abstracts while containing almost all given content from their abstracts. In the patents from the TREC Chemistry Track, it is even more extreme. Especially the description section includes almost all entities mentioned in a patent and contains in comparison to the claim section at least 79 % of all entities exclusively.
 

Bernd Müller (1,2), Roman Klinger (1), Harsha Gurulingappa (1,2), Heinz-Theodor Mevissen (1), Martin Hofmann-Apitius (1,2), Juliane Fluck (1), and Christoph M. Friedrich (1)

1 Fraunhofer Institute for Algorithms and Scientic Computing (SCAI),

2 Bonn-Aachen International Center for Information Technology (B-IT)