Synonym Extraction of Medical Terms from Clinical Text Using Combinations of Word Space Models
2012 (English)In: Proceedings of the 5th International Symposium on Semantic Mining in Biomedicine (SMBM 2012), 2012, 10-17 p.Conference paper (Refereed)
In information extraction, it is useful to know if two signifiers have the same or very similar semantic content. Maintaining such information in a controlled vocabulary is, however, costly. Here it is demonstrated how synonyms of medical terms can be extracted automatically from a large corpus of clinical text using distributional semantics. By combining Random Indexing and Random Permutation, different lexical semantic aspects are captured, effectively increasing our ability to identify synonymic relations between terms. 44% of 340 synonym pairs from MeSH are successfully extracted in a list of ten suggestions. The models can also be used to map abbreviations to their full-length forms; simple pattern-based filtering of the suggestions yields substantial improvements.
Place, publisher, year, edition, pages
2012. 10-17 p.
synonyms, abbreviations, distributional semantics, word space model, random indexing, random permutation, clinical text
Research subject Computer and Systems Sciences
IdentifiersURN: urn:nbn:se:su:diva-85441DOI: 10.5167/uzh-64476ISBN: 978-3-033-03823-3OAI: oai:DiVA.org:su-85441DiVA: diva2:583702
5th International Symposium on Semantic Mining in Biomedicine (SMBM), September 3-4 2012, Zurich, Switzerland