Abstract
We describe a cross-corpora evaluation of disease mention recognition for two annotated biomedical corpora: the Human Variome Project Corpus and the Arizona Disease Corpus. Our analysis of the performance of a state-of-the-art NER tool in terms of the characteristics and annotation schema of these corpora shows that these factors significantly affect performance.
| Original language | English |
|---|---|
| Title of host publication | Australasian Language Technology Association Workshop 2013 - Proceedings of the Workshop (ALTA) |
| Editors | Sarvnaz Karimi, Karin Verspoor |
| Place of Publication | Stroudsburg PA USA |
| Publisher | Association for Computational Linguistics (ACL) |
| Pages | 91-95 |
| Number of pages | 5 |
| Publication status | Published - 2013 |
| Event | Australasian Language Technology Association Workshop 2013 - Queensland University of Technology, Brisbane, Australia Duration: 4 Dec 2013 → 6 Dec 2013 Conference number: 11th https://www.aclweb.org/anthology/events/alta-2013/ (Proceedings) |
Conference
| Conference | Australasian Language Technology Association Workshop 2013 |
|---|---|
| Abbreviated title | ALTAW 2013 |
| Country/Territory | Australia |
| City | Brisbane |
| Period | 4/12/13 → 6/12/13 |
| Internet address |
|