Neural architecture for temporal relation extraction: A Bi-LSTM approach for detecting narrative containers
Fiche du document
30 juillet 2017
- handle: 10670/1.8ayasi
- cea-01841667
- doi: 10.18653/v1/P17-2035
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.18653/v1/P17-2035
Mots-clés
Clinical notes Computational linguistics F measure Neural architectures Temporal relation Temporal expressions LinguisticsSujets proches
Linguistics--Data processing Language and languages--Data processing Language data processing Natural language processing (Linguistics) Automatic language processing Date Western architecture (Western countries) Building design Construction Buildings--Design and construction Architecture, Western (Western countries)Citer ce document
J. Tourille et al., « Neural architecture for temporal relation extraction: A Bi-LSTM approach for detecting narrative containers », HAL-SHS : sciences de l'information, de la communication et des bibliothèques, ID : 10.18653/v1/P17-2035
Métriques
Partage / Export
Résumé
We present a neural architecture for containment relation identification between medical events and/or temporal expressions. We experiment on a corpus of de-identified clinical notes in English from the Mayo Clinic, namely the THYME corpus. Our model achieves an F-measure of 0.613 and outperforms the best result reported on this corpus to date.