Important Updates/Final CFP: MEDDOPLACE (place, location & travel NER/linking form health texts) Shared Task
- NEW: Annotation guidelines - English version released & generated corpus subset for English, French, Italian, Portuguese and Romanian.
-
NEW Guidelines English: https://zenodo.org/record/7928146
Info:
-
Web: https://temu.bsc.es/meddoplace/ -
Registration: https://temu.bsc.es/meddoplace/registration -
Data: https://zenodo.org/record/7707567 -
Guidelines Spanish: https://zenodo.org/record/7775235 -
CodaLab: https://codalab.lisn.upsaclay.fr/competitions/13017
MOTIVATION
Location information represents one of the most relevant types of entities for high impact practical NLP solutions, resulting in a variety of applications adapted to different languages, content types and text genres.
We organize the MEDDOPLACE shared task (Medical Documents PLAce-related Content Extraction, part of the IberLEF/SEPLN2023 initiative) devoted to the recognition, normalization and classification of location and location-related concept mentions for high impact healthcare data mining scenarios.
For this task we released the MEDDOPLACE corpus of clinical case texts in Spanish annotated with location-relevant entity mentions, following annotation guidelines and entity linking procedures.
Practical impact:
-
Diagnosis & prognosis: Location information is important for the diagnosis or prognosis of some diseases that are more endemic to certain regions or particular geographical environments. -
Health risk factors: Geolocation information can be a risk factor in case of exposure to radiation, work-related or environmental contaminants affecting patients health. -
Mobility: Due to the increasing mobility of populations, detection of patients' travels and movements can improve early detection and tracing of infectious disease outbreaks, and thus enable taking preventive measurements.
The expected results and resources show a multilingual adaptation potential and impact beyond healthcare (e.g. adaptation to tourism/traveling-related content or legal texts).
TASKS SUBTRACKS:
1.
Location Entity Recognition: detect exact character offsets of all location & location-related mentions. 2.
Geographic Entity Normalization (Geocoding/Entity Linking): for entity mentions, normalize them to their GeoNames (Toponym Resolution), PlusCodes (POIs Toponym Resolution) & SNOMED CT (Entity Linking) concept, depending on entity type. 3.
Entity Subclassification: Classification of entity mentions into four subcategories of clinical relevance (patient’s origin place; residence’s location; place where the patient has traveled to/from; place where the patient has received medical attention) 4.
End-to-End: Participant systems are evaluated in all three tasks above sequentially instead of being evaluated on their own.
Publications & workshop
Teams participating will be invited to contribute a systems description paper for the IberLEF (SEPLN 2023) Working Notes proceedings, and a short presentation of their approach at the IberLEF 2023 workshop, see: https://temu.bsc.es/meddoplace/publications/.
Tentative Schedule:
-
End of evaluation Phase 1: May 31st, 2023 -
End of evaluation Phase 2: June 12th, 2023 -
Working papers submission: June 14th, 2023 -
Notification of acceptance (peer-reviews): June 26th, 2023 -
Camera-ready system descriptions: July 5th, 2023 -
IberLEF @ SEPLN 2023: September 27th-29th, 2023
Organizers:
-
Martin Krallinger, Barcelona Supercomputing Center, Spain -
Salvador Lima, Barcelona Supercomputing Center, Spain -
Eulàlia Farré, Barcelona Supercomputing Center, Spain -
Luis Gascó, Barcelona Supercomputing Center, Spain -
Vicent Briva-Iglesias, D-REAL, Dublin City University, Ireland
======================================= Martin Krallinger, Dr. Head of NLP for Biomedical Information Analysis Unit Barcelona Supercomputing Center (BSC-CNS) https://www.linkedin.com/in/martin-krallinger-85495920/ =======================================