Relation extraction

This task aims to detect entities and semantic relations between them in e-Health documents. 

It comprises 4 entity types (concept, action, predicate, and reference) and the following relations:

  • General relations (6): general-purpose relations between two concepts that have a specific semantic: is-a, same-as, has-property, part-of, causes, and entails.
  • Contextual relations (3): allow a concept to be refined by attaching the modifiers: in-time, in-place, and in-context.
  • Action roles (2): indicate which concepts play a role related to an Action, which can be subject and target.
  • Predicate roles (2): indicate concepts play a role in relation to a Predicate, which can be the domain and additional arguments.
Publication
Alejandro Piad-Morffis, Yoan Gutiérrez, Juan Pablo Consuegra-Ayala, Suilan Estevez-Velarde, Yudivián Almeida-Cruz, Rafael Muñoz, Andrés Montoyo (2019) Overview of the eHealth Knowledge Discovery Challenge at IberLEF 2019. Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2019)
Language
Spanish
Abstract task
Dataset
Year
2019
Ranking metric
F1

Task results

System F1 Sort ascending
TALP-UPC 0.6260
NLP_UNED 0.5330
VSP 0.4930
coin_flipper 0.4930
UH-MIXAMedaja-KD 0.4350

If you have published a result better than those on the list, send a message to odesia-comunicacion@lsi.uned.es indicating the result and the DOI of the article, along with a copy of it if it is not published openly.