Published February 14, 2021
| Version 3.0
Dataset
Open
CORD-19 Diachronic Concept Embeddings
Authors/Creators
- 1. University of Pittsburgh
- 2. Carnegie Mellon University
- 3. The Ohio State University
Description
Medical concept embeddings trained on monthly releases of the CORD-19 dataset, for analysis of diachronic change.
This resource includes:
- Concept embeddings, trained using the JET toolkit on the set of articles added to CORD-19 in each month of March 2020 - October 2020. Concepts are SNOMED CT codes.
- Nearest neighborhood-based analysis results of the concept embeddings, stored as a SQLite database.
Database content excludes terms and definitions for SNOMED CT codes, which are licensed content owned by SNOMED International. Information on accessing SNOMED licensed content may be found here.
Files
CORD-19_monthly_embeddings.zip
Additional details
Related works
- References
- Conference paper: 10.18653/v1/W18-3026 (DOI)