|
University of Minnesota Digital Conservancy >
University of Minnesota - Twin Cities >
Institute for Health Informatics >
Research Data >
Please use this permanent URL to cite or link to this item:
http://purl.umn.edu/137704
|
| Title: | Clinical Symbol Sense Inventory |
| Authors: | Moon, Sungrim
Pakhomov, Serguei
Melton, Genevieve |
| Keywords: | clinical
symbol
disambiguation
inventory
sense |
| Issue Date: | 31-Oct-2012 |
| Abstract: | Although clinical texts contain many symbols, relatively little attention has been given to symbol resolution by medical natural language processing (NLP) researchers. Interpreting the meaning of symbols may be viewed as a special case of Word Sense Disambiguation (WSD). One thousand instances of four common non-alphanumeric symbols (‘+’, ‘–’, ‘/’, and ‘#’) were randomly extracted from a clinical document repository and annotated by experts. De-identified data are available for researchers. |
| Permanent URL: | http://purl.umn.edu/137704 |
| Appears in Collections: | Research Data
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| DeidentifedSymbolDataSet.txt | De-identified symbol dataset | 1238Kb | Text | View/Open | | README_DeidentifedSymbolDataSet.txt | README for De-identified symbol dataset | 3Kb | Text | View/Open |
|
Items in the Digital Conservancy are protected by copyright, with all rights reserved, unless otherwise indicated.
|
