Affiliations: EML Research gGmbH, D-69118 Heidelberg, Germany.
E-mail: saric@eml-r.org, rojas@eml-r.org | European Molecular Biology Laboratory, D-69117
Heidelberg, Germany. E-mail: jensen@embl.de
Note: [] Corresponding author
Abstract: This paper presents an approach using syntactosemantic rules for the
extraction of relational information from biomedical abstracts. The results
show that by overcoming the hurdle of technical terminology, high precision
results can be achieved. From abstracts related to baker's yeast, we manage to
extract a regulatory network comprised of 441 pairwise relations from 58,664
abstracts with an accuracy of 83–90%. To achieve this, we made use of a
resource of gene/protein names considerably larger than those used in most
other biology related information extraction approaches. This list of names was
included in the lexicon of our retrained partof- speech tagger for use on
molecular biology abstracts. For the domain in question an accuracy of
93.6–97.7% was attained on Part-of-speech-tags. The method can be easily
adapted to other organisms than yeast, allowing us to extract many more
biologically relevant relations. The main reason for the comparable precision
rates is the ontological model that was built beforehand and served as a
guiding force for the manual coding of the syntactosemantic rules. Preliminary results on journal articles from PubMed Central suggest
that our rule set performs with equal accuracy when applied to full text rather
than abstracts.
Keywords: ontologies, information extraction, bionlp, natural language processing
