Coreference Resolution for French Oral Data: Machine Learning Experiments with ANCOR

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 come exclusively from transcribed speech, namely ANCOR (ANaphora and Corefer-ence in ORal corpus), the first large-scale French corpus with anaphorical relation annotations. In its current state, the CROC system requires pre-annotated mentions. We detail the features used for 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.
Document type :
Book sections
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01889593
Contributor : Jean-Yves Antoine <>
Submitted on : Sunday, October 7, 2018 - 9:45:48 AM
Last modification on : Thursday, February 7, 2019 - 4:54:11 PM
Document(s) archivé(s) le : Tuesday, January 8, 2019 - 12:34:02 PM

File

18_Cicling.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01889593, version 1

Citation

Adèle Désoyer, Frédéric Landragin, Isabelle Tellier, Anaïs Lefeuvre-Halftermeyer, Jean-Yves Antoine, et al.. Coreference Resolution for French Oral Data: Machine Learning Experiments with ANCOR. Computational Linguistics and Intelligent Text Processing., n° 9623-9624, 2018, Lecture Notes in Computer Science. ⟨hal-01889593⟩

Share

Metrics

Record views

56

Files downloads

23