The eHealth Knowledge Discovery Challenge, hosted at IberLEF 2019, proposes an evaluation task for the automatic identification of key phrases and the semantic relations between them in health-related documents in Spanish language. This paper describes the challenge design, evaluation metrics, participants and main results. The most promising approaches are analyzed and the significant challenges are highlighted and discussed. Analysis of the participant systems shows an overall trend of sequence-based deep learning architectures coupled with domain-specific or domain-agnostic unsupervised language representations. Successful approaches suggest that modeling the problem as an end-to-end learning task rather than separated in two subtasks improves performance. Interesting lines for future development were recognized, such as the option of increasing the corpus size with semi-automated approaches and designing more robust evaluation metrics.
Revista: IberLEF
Autores: Alejandro Piad-Morffis, Yoan Gutiérrez, Juan Pablo Consuegra-Ayala, Suilan Estevez-Velarde, Yudivián Almeida-Cruz, Rafael Muñoz, Andrés Montoyo
URL: http://ceur-ws.org/Vol-2421/eHealth-KD_overview.pdf