Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral French - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2019

Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral French

Résumé

We propose an end-to-end coreference resolution system obtained by adapting neural models that have recently improved the state-of-the-art on the OntoNotes benchmark to make them applicable to other paradigms for this task. We report the performances of our system on ANCOR, a corpus of transcribed oral French-for which it constitutes a new baseline with proper evaluation.
Fichier principal
Vignette du fichier
naacl2019.pdf (77.05 Ko) Télécharger le fichier
W19-2802-supplementary.tar.gz (35.64 Ko) Télécharger le fichier
slides.pdf (978.54 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02151569 , version 1 (08-06-2019)
hal-02151569 , version 2 (23-09-2019)

Licence

Identifiants

  • HAL Id : hal-02151569 , version 1

Citer

Loïc Grobol. Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral French. Second Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC19), Jun 2019, Minneapolis, United States. ⟨hal-02151569v1⟩
291 Consultations
554 Téléchargements

Partager

More