French coreference for spoken and written language - HAL-SHS - Sciences de l'Homme et de la Société Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

French coreference for spoken and written language

Résumé

Coreference resolution aims at identifying and grouping all mentions referring to the same entity. In French, most systems run different setups, making their comparison difficult. In this paper, we present an extensive comparison of several coreference resolution systems for French. The systems have been trained on two corpora (ANCOR for spoken language and Democrat for written language) annotated with coreference chains, and augmented with syntactic and semantic information. The models are compared with different configurations (e.g. with and without singletons). In addition, we evaluate mention detection and coreference resolution apart. We present a full-stack model that outperforms the other approaches. This model allows us to study the impact of mention detection errors on coreference resolution. Our analysis shows that mention detection can be improved focusing on boundary identification while advances in the pronoun-noun relation detection can aid the coreference task. Another contribution of this work is the first end-to-end neural French coreference resolution model trained on Democrat (written texts), which compares to the state-of-the-art systems for oral French.
Fichier principal
Vignette du fichier
2020.lrec-1.10.pdf (400.02 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02476902 , version 1 (04-06-2020)

Identifiants

  • HAL Id : hal-02476902 , version 1

Citer

Rodrigo Wilkens, Bruno Oberle, Frédéric Landragin, Amalia Todirascu. French coreference for spoken and written language. Language Resources and Evaluation Conference (LREC 2020), 2020, Marseille, France. pp.80-89. ⟨hal-02476902⟩
425 Consultations
306 Téléchargements

Partager

Gmail Facebook X LinkedIn More