This task aims to detect semantic relations between entities in technical documents, including encyclopedias, news, and scientific papers.
It comprises 4 entity types (concept, action, predicate, and reference) and 13 relations: is-a, same-as, part-of, has-property, causes, entails, in-time, in-place, in-context, subject, target, domain, and arg.
Publication
Alejandro Piad-Morfis, Suilan Estevez-Velarde, Yoan Gutierrez, Yudivian Almeida-Cruz, Andrés Montoyo, Rafael Muñoz (2021) Overview of the eHealth Knowledge Discovery Challenge at IberLEF 2021. Procesamiento del Lenguaje Natural, Revista nº 67, septiembre de 2021, pp. 233-242
Competition
Language
Spanish
English
NLP topic
Abstract task
Dataset
Year
2021
Publication link
Ranking metric
F1
Task results
System | Precision | Recall | F1 Sort ascending |
---|---|---|---|
IXA | 0.4530 | 0.4090 | 0.4300 |
Vicomtech | 0.5410 | 0.2830 | 0.3710 |
uhKD4 | 0.5560 | 0.2220 | 0.3170 |
PUCRJ-PUCPR-UFMG | 0.3660 | 0.2050 | 0.2630 |
UH-MMM | 0.0770 | 0.0410 | 0.0530 |