On-demand new word learning using world wide web - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

On-demand new word learning using world wide web

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. Our experiments confirm the relevance of the Web for the OOV word retrieval. Different methods are proposed to retrieve the hypothesis words. Finally we present the integration of new words in the transcription process based on part-of-speech models. This technique allows to recover 7.6% of the significant OOV words and the accuracy of the system is improved.
Fichier non déposé

Dates et versions

hal-01319857 , version 1 (23-05-2016)

Identifiants

Citer

Stanislas Oger, Georges Linarès, Frédéric Béchet, Pascal Nocera. On-demand new word learning using world wide web. IEEE International Conference on Acoustics, Speech and Signal Processing , Mar 2008, Las Vegas, United States. ⟨10.1109/ICASSP.2008.4518607⟩. ⟨hal-01319857⟩

Collections

UNIV-AVIGNON LIA
100 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More