Talp-UPC at eHealth-KD challenge 2019: A joint model with contextual embeddings for clinical information extraction
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/169003
Tipus de documentText en actes de congrés
Data publicació2019
EditorCEUR-WS.org
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement 3.0 Espanya
Projecte
Abstract
Most eHealth entity recognition and relation extraction models tackle the identification of entities and relations with independent specialized models. In this article, we show how a single combined model can exploit the correlation between these two tasks to improve the evaluation score of both, while reducing training and execution time. Our model uses both traditional part-of-speech tagging and dependency-parsing of
the documents and state-of-the-art pre-trained Contextual Embeddings as input features. Furthermore, Long-Short Term Memory units are used to model close relationships between words while convolution filters are applied for farther dependencies. Our model was able to get the highest score in all three tasks of IberLEF2019’s eHealth-KD competition[7].
This advantage was specially promising in the relation extraction tasks, in which it outperformed the second best model by a margin of 9.3% in F1 Score.
CitacióMedina, S.; Turmo, J. Talp-UPC at eHealth-KD challenge 2019: A joint model with contextual embeddings for clinical information extraction. A: Iberian Languages Evaluation Forum. "Proceedings of the Iberian Languages Evaluation Forum (IberLEF 2019): co-located with 35th Conference of the Spanish Society for Natural Language Processing (SEPLN 2019): Bilbao, Spain, September 24th, 2019". CEUR-WS.org, 2019, p. 78-84.
ISSN1613-0073
Versió de l'editorhttp://ceur-ws.org/Vol-2421/eHealth-KD_paper_8.pdf
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
eHealth-KD_paper_8.pdf | 1,028Mb | Visualitza/Obre |