CIAD System for Geographical Entity Detection at TextMine'24 - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

CIAD System for Geographical Entity Detection at TextMine'24

Résumé

This paper outlines CIAD's approach to Named Entity Recognition (NER) in a corpus of nautical instruction. Employing a conventional entity detection approach, our system tackles the NER task through token classification. We handled this classification task using two approaches: 1. NER is performed using different BERT models (BERT-base, Tiny-BERT, and CamemBERT); 2. We also used a GCN-based token classification where a graph is built connecting words in the same context. Our results suggest that within these token classification setups, our models are bounded to an accuracy of around 92% on the test data regardless of the complexity of the used BERT model.
Fichier principal
Vignette du fichier
TextMine24_paper_8-6.pdf (95.19 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04455869 , version 1 (13-02-2024)

Licence

Paternité

Identifiants

  • HAL Id : hal-04455869 , version 1

Citer

Pauline Armary, Cheikh Brahim El Vaigh, Ouassila Labbani Narsis, Christophe Nicolle. CIAD System for Geographical Entity Detection at TextMine'24. TextMine'24, Jan 2024, Dijon, France. ⟨hal-04455869⟩
39 Consultations
23 Téléchargements

Partager

Gmail Facebook X LinkedIn More