Speculation and negation detection in french biomedical corpora - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Speculation and negation detection in french biomedical corpora

Résumé

In this work, we propose to address the detection of negation and speculation, and of their scope, in French biomedical documents. It has been indeed observed that they play an important role and provide crucial clues for other NLP applications. Our methods are based on CRFs and BiLSTM. We reach up to 97.21 % and 91.30 % F-measure for the detection of negation and speculation cues, respectively , using CRFs. For the computing of scope, we reach up to 90.81 % and 86.73 % F-measure on negation and speculation , respectively, using BiLSTM-CRF fed with word embeddings.
Fichier principal
Vignette du fichier
RANLP2019(1).pdf (166.78 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02284444 , version 1 (11-09-2019)

Licence

Paternité

Identifiants

  • HAL Id : hal-02284444 , version 1

Citer

Clément Dalloux, Vincent Claveau, Natalia Grabar. Speculation and negation detection in french biomedical corpora. RANLP 2019 - Recent Advances in Natural Language Processing, Sep 2019, Varna, Bulgaria. pp.1-10. ⟨hal-02284444⟩
190 Consultations
494 Téléchargements

Partager

Gmail Facebook X LinkedIn More