Browsing by Author "Medina Herrera, Salvador"
Now showing items 1-8 of 8
-
Appnalyze
(Universitat Politècnica de Catalunya, 2015-05-29)
Master thesis (pre-Bologna period)
Open AccessEste proyecto tiene por objetivo presentar y analizar las bases de una posible solución al problema anteriormente planteado. Estudiaremos la aplicación técnicas de Machine Learning, en particular de diferentes modelos ... -
Bootstrapping for electronic health record anonymization with minimal supervision
(Universitat Politècnica de Catalunya, 2017-01-25)
Master thesis
Open AccessIn this work, we propose a bootstrapping strategy so as to enrich anonymization models for Catalan medical reports taking profit of huge sets of unlabeled documents. -
Building a Spanish/Catalan health records corpus with very sparse protected information labelled
(2018)
Conference lecture
Open AccessElectronic Health Records (EHR) are an important resource for the research and study of diseases, treatments and symptoms. However, due to data protection laws, information that could potentially compromise privacy must ... -
Everything transformers: Recognition, classification and normalisation of professions and family relations
(CEUR-WS.org, 2021)
Conference report
Open AccessThis document describes the system submitted by TALP team for IberLEF 2021’s MEDDOPROF Shared Task. The joint occupation mention identification and family relation classification model is composed of a pre-trained DistilBERT ... -
Joint classification of key-phrases and relations in electronic health documents
(CEUR-WS.org, 2018)
Conference report
Open AccessThis paper describes the approach presented by the TALP team for Task 3 of TASS-2018: a convolutional neural network to jointly deal with classification of key-phrases and relationships in eHealth documents written in ... -
Semi-supervised learning for disabilities detection on English and Spanish biomedical text
(2018)
Conference report
Open AccessThis paper describes the disability detection model approaches presented by UPC’s TALP 3 team for the DIANN 2018 shared task. The best of those approaches was ranked in 3rd place for exact-matching of disability detection. ... -
TALP at eHealth-KD Challenge 2020: Multi-level recurrent and convolutional neural networks for joint classification of key-phrases and relations
(CEUR-WS.org, 2020)
Conference report
Open AccessThis article describes the model presented by the TALP Team to IberLEF’s eHealth Knowledge Discovery 2020 shared task[1]. The model iterates over the idea of using a single model for simultaneously identify key-phrases and ... -
Talp-UPC at eHealth-KD challenge 2019: A joint model with contextual embeddings for clinical information extraction
(CEUR-WS.org, 2019)
Conference report
Open AccessMost 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 ...
