Skip to Main content Skip to Navigation
Conference papers

Apprentissage automatique d'un modèle de résolution de la coréférence à partir de données orales transcrites du français : le système CROC

Abstract : We present CROC (Coreference Resolution for Oral Corpus), the first machine learning system for coreference resolution in French. One specific aspect of the system is that it has been trained on data that are exclusively oral, namely ANCOR (ANaphora and Coreference in ORal corpus), the first corpus in oral French with anaphorical relations annotations. In its current state, the CROC system requires pre-annotated mentions. We detail the features that we chose to be used by the learning algorithms, and we present a set of experiments with these features. The scores we obtain are close to those of state-of-the-art systems for written English. Then we give future works on the design of an end-to-end system for oral and written French.
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://halshs.archives-ouvertes.fr/halshs-01162174
Contributor : Frédéric Landragin <>
Submitted on : Tuesday, June 16, 2015 - 5:30:27 PM
Last modification on : Tuesday, September 22, 2020 - 3:45:31 AM
Long-term archiving on: : Tuesday, April 25, 2017 - 5:48:45 AM

File

15_TALN.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : halshs-01162174, version 1

Citation

Adèle Désoyer, Frédéric Landragin, Isabelle Tellier. Apprentissage automatique d'un modèle de résolution de la coréférence à partir de données orales transcrites du français : le système CROC. Vingt-deuxième Conférence sur le Traitement Automatique des Langues Naturelles, Jun 2015, Caen, France. pp.439-445. ⟨halshs-01162174⟩

Share

Metrics

Record views

457

Files downloads

666