LIMSI at CEGS N-GRID 2016 NLP Shared-Tasks: Track 1.B De-Identification of Clinical Texts at Character and Token Levels
Overview & Synopsis
Track 1.B of the CEGS N-GRID 2016 NLP Shared-Tasks consisted in automatically de-identifying clinical texts. The training dataset is composed of 600 texts annotated into 7 main categories of PHI (AGE, CONTACT, DATE, ID, LOCATION, NAME, PROFESSION) . The test dataset is composed of 400 unannotated texts. A tokenization issue occurred in both corpora: a high proportion of end-of-lines were removed, producing run-in words, i.e., sequences of two tokens where it may happen that only one token must be de-identified (e.g., “11/20/2073CPT”).
Indexed from repository: HAL Open Science
(
hal.science)
Keyboard Shortcuts:
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | LIMSI at CEGS N-GRID 2016 NLP Shared-Tasks: Track 1.B De-Identification of Clinical Texts at Character and Token Levels |
|---|---|
| Author / Organization | Cyril Grouin |
| Subject & Discipline | Multidisciplinary Academic Open Research |
| Categories | Science & Mathematics |
| Publication Year | 2016 |
| License / Rights | Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
HAL Open Science
(hal.science)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-229199 |
| Original Source Link | Visit Source Page on hal.science » |