Anatomical Entity Recognition with Open Biomedical Ontologies
Lists
Only you see this
Abstract
Anatomical entities are central to much of biomedical discourse and must be considered in any attempt to fully analyse biomedical scientific text. However, while a wealth of tools and resources have been introduced in domain natural language processing efforts for the recognition of mentions of biomolecules and organisms in text, there has been little study of anatomical entities such as tissues and organs. In this paper, we consider the closely related tasks of distinguishing terms that refer to anatomical entities from ones that do not and assigning the former into upper-level semantic classes. We draw on the wealth of anatomical domain resources available in the Open Biomedical Ontologies repository, evaluating entity detection performance using the ontologies against a manually curated corpus of 5000 phrases occurring with high frequency in PubMed. We further analyse the upper-level structure of these ontologies to determine whether the resources offer a stable basis for speciesindependent classification and discuss remaining conflicts and challenges.
BibTeX
@inproceedings{pyysalo2011anatomical,
author = {Sampo Pyysalo and Tomoko Ohta and Sophia Ananiadou},
title = {{Anatomical Entity Recognition with Open Biomedical Ontologies}},
booktitle = {Research},
year = {2011},
}Loading related content...