Journal
BIOINFORMATICS
Volume 36, Issue 7, Pages 2224-2228Publisher
OXFORD UNIV PRESS
DOI: 10.1093/bioinformatics/btz923
Keywords
-
Ask authors/readers for more resources
Motivation: Name ambiguity has long been a central problem in biomedical text mining. To tackle it, it has been usually assumed that names present only one meaning within a given text. It is not known whether this assumption applies beyond the scope of single documents. Results: Using a new method that leverages large numbers of biomedical annotations and normalized citations, this study shows that ambiguous biomedical names mentioned in scientific articles tend to present the same meaning in articles that cite them or that they cite, and, to a lesser extent, two steps away in the citation network. Citations, therefore, can be regarded as semantic connections between articles and the citation network should be considered for tasks such as automatic name disambiguation, entity linking and biomedical database annotation. A simple experiment shows the applicability of these findings to name disambiguation.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available