French text preprocessing with TTL - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Proceedings of the Romanian Academy - Series A (Mathematics, Physics, Technical Sciences, Information Science) Année : 2011

French text preprocessing with TTL

Amalia Todirascu
Radu Ion
  • Fonction : Auteur
  • PersonId : 945981
Mirabela Navlea
  • Fonction : Auteur
  • PersonId : 945982
Laurence Longo

Résumé

In this paper we present some experiments on the building of French resources for the TTL POS tagger (Ion, 2007). TTL is a collection of interconnected text preprocessing modules (sentence splitter, tokenizer, tagger, le mmatizer and chunker) with resources for Romanian and English but with no resources available for French. We show how we develop the required POS tagging training corpus and that the average POS tagging accuracy for French exceeds 97% when TTL is trained on this corpus.

Domaines

Informatique
Fichier non déposé

Dates et versions

hal-00867452 , version 1 (29-09-2013)

Identifiants

  • HAL Id : hal-00867452 , version 1

Citer

Amalia Todirascu, Radu Ion, Mirabela Navlea, Laurence Longo. French text preprocessing with TTL. Proceedings of the Romanian Academy - Series A (Mathematics, Physics, Technical Sciences, Information Science), 2011, 12 (2), pp. 151-158. ⟨hal-00867452⟩

Collections

SITE-ALSACE
182 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More