Local methods for on-demand out-of-vocabulary word retrieval - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Local methods for on-demand out-of-vocabulary word retrieval

Stanislas Oger
  • Fonction : Auteur
  • PersonId : 770872
  • IdRef : 176527176
Georges Linarès
Frédéric Béchet

Résumé

Most of the Web-based methods for lexicon augmenting consist in capturing global semantic features of the targeted domain in order to collect relevant documents from the Web. We suggest that the local context of the out-of-vocabulary (OOV) words contains relevant information on the OOV words. With this information, we propose to use the Web to build locally-augmented lexicons which are used in a final local decoding pass. First, an automatic web based OOV word detection method is proposed. Then, we demonstrate the relevance of the Web for the OOV word retrieval. Different methods are proposed to retrieve the hypothesis words. We finally retrieve about 26% of the OOV words with a lexicon increase of less than 1000 words using the reference context.
Fichier non déposé

Dates et versions

hal-01319850 , version 1 (23-05-2016)

Identifiants

  • HAL Id : hal-01319850 , version 1

Citer

Stanislas Oger, Georges Linarès, Frédéric Béchet. Local methods for on-demand out-of-vocabulary word retrieval. LREC, May 2008, Marrakech, Morocco. ⟨hal-01319850⟩

Collections

UNIV-AVIGNON LIA
88 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More