IAI @ SocialDisNER: Catch me if you can! Capturing complex disease mentions in tweets - Archive ouverte HAL Accéder directement au contenu
Proceedings/Recueil Des Communications Année : 2022

IAI @ SocialDisNER: Catch me if you can! Capturing complex disease mentions in tweets

Résumé

Biomedical NER is an active research area today. Despite the availability of state-of-theart models for standard NER tasks, their performance degrades on biomedical data due to OOV entities and the challenges encountered in specialized domains. We use Flair-NER framework to investigate the effectiveness of various contextual and static embeddings for NER on Spanish tweets, in particular, to capture complex disease mentions.
Fichier principal
Vignette du fichier
2022.smm4h-1.25.pdf (222.47 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY - Paternité

Dates et versions

hal-04155125 , version 1 (07-07-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04155125 , version 1

Citer

Aman Sinha, Cristina García Holgado, Marianne Clausel, Mathieu Constant. IAI @ SocialDisNER: Catch me if you can! Capturing complex disease mentions in tweets. Association for Computational Linguistics, pp.85-89, 2022. ⟨hal-04155125⟩
9 Consultations
27 Téléchargements

Partager

Gmail Facebook X LinkedIn More