Unsupervised knowledge acquisition for Extracting Named Entities from speech - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Unsupervised knowledge acquisition for Extracting Named Entities from speech

Eric Charton
  • Fonction : Auteur
  • PersonId : 981922

Résumé

This paper presents a Named Entity Recognition (NER) method dedicated to process speech transcriptions. The main principle behind this method is to collect in an unsupervised way lexical knowledge for all entries in the ASR lexicon. This knowledge is gathered with two methods: by automatically extracting NEs on a very large set of textual corpora and by exploiting directly the structure contained in the Wikipedia resource. This lexical knowledge is used to update the statistical models of our NER module based on a mixed approach with generative models (Hidden Markov Models-HMM) and discriminative models (Conditional Random Field-CRF). This approach has been evaluated within the French ESTER 2 evaluation program and obtained the best results at the NER task on ASR transcripts .
Fichier non déposé

Dates et versions

hal-01312857 , version 1 (09-05-2016)

Identifiants

Citer

Frederic Bechet, Eric Charton. Unsupervised knowledge acquisition for Extracting Named Entities from speech. IEEE International Conference on Acoustics, Speech and Signal Processing , Mar 2010, Dallas, United States. ⟨10.1109/ICASSP.2010.5494962⟩. ⟨hal-01312857⟩
73 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More