Towards the Automatic Processing of Language Registers: Semi-supervisedly Built Corpus and Classifier for French
Fiche du document
7 avril 2019
- handle: 10670/1.lw0w0w
- hal: hal-02064694
- doi: 10.1007/978-3-031-24337-0_34
Ce document est lié à :
info:eu-repo/semantics/altIdentifier/doi/10.1007/978-3-031-24337-0_34
info:eu-repo/semantics/OpenAccess
Sujets proches
Registers, lists, etcCiter ce document
Gwénolé Lecorvé et al., « Towards the Automatic Processing of Language Registers: Semi-supervisedly Built Corpus and Classifier for French », HAL-SHS : linguistique, ID : 10.1007/978-3-031-24337-0_34
Métriques
Partage / Export
Résumé
Language registers are a strongly perceptible characteristic of texts and speeches. However, they are still poorly studied in natural language processing. In this paper, we present a semi-supervised approach which jointly builds a corpus of texts labeled in registers and an associated classifier. This approach relies on a small initial seed of expert data. After massively retrieving web pages, it iteratively alternates the training of an intermediate classifier and the annotation of new texts to augment the labeled corpus. The approach is applied to the casual, neutral, and formal registers, leading to a 750M word corpus and a final neural classifier with an acceptable performance.