Title
|
|
|
|
Using distributed representations to disambiguate biomedical and clinical concepts
|
|
Author
|
|
|
|
|
|
Abstract
|
|
|
|
In this paper, we report a knowledge-based method for Word Sense Disambiguation in the domains of biomedical and clini- cal text. We combine word representa- tions created on large corpora with a small number of definitions from the UMLS to create concept representations, which we then compare to representations of the con- text of ambiguous terms. Using no re- lational information, we obtain compara- ble performance to previous approaches on the MSH-WSD dataset, which is a well-known dataset in the biomedical do- main. Additionally, our method is fast and easy to set up and extend to other do- mains. Supplementary materials, includ- ing source code, can be found at https: //github.com/clips/yarn |
|
|
Language
|
|
|
|
English
|
|
Source (book)
|
|
|
|
Proceedings of the 15th Workshop on Biomedical Natural Language Processing of the Association for Computational Linguistics
|
|
Publication
|
|
|
|
Berlin
:
Association for Computational Linguistics
,
2016
|
|
ISBN
|
|
|
|
978-1-945626-12-8
|
|
Volume/pages
|
|
|
|
p. 77-82
|
|
Full text (publisher's version - intranet only)
|
|
|
|
|
|