| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 10320528 | Artificial Intelligence in Medicine | 2015 | 9 Pages |
Abstract
We conclude that gold-standard data are not a hard requirement for drug NER. Combining heterogeneous models build on dictionary knowledge can achieve similar or comparable classification performance with that of the best performing model trained on gold-standard annotations.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Ioannis Korkontzelos, Dimitrios Piliouras, Andrew W. Dowsey, Sophia Ananiadou,