Disentangling ASR and MT Errors in Speech Translation

Abstract : The main aim of this paper is to investigate automatic quality assessment for spoken language translation (SLT). More precisely, we investigate SLT errors that can be due to transcription (ASR) or to translation (MT) modules. This paper investigates automatic detection of SLT errors using a single classifier based on joint ASR and MT features. We evaluate both 2-class (good/bad) and 3-class (good/badASR/badMT) labeling tasks. The 3-class problem necessitates to disentangle ASR and MT errors in the speech translation output and we propose two label extraction methods for this non trivial step. This enables-as a by-product-qualitative analysis on the SLT errors and their origin (are they due to transcription or to translation step?) on our large in-house corpus for French-to-English speech translation.
Type de document :
Communication dans un congrès
MT Summit 2017, Sep 2017, Nagoya, Japan. MT Summit 2017 proceedings, 〈http://aamt.info/app-def/S-102/mtsummit/2017/〉
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01580877
Contributeur : Laurent Besacier <>
Soumis le : dimanche 3 septembre 2017 - 11:55:05
Dernière modification le : mercredi 25 octobre 2017 - 10:50:01

Fichier

DisentanglingASR_and_MT_errors...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01580877, version 1

Collections

Citation

Ngoc-Tien Le, Benjamin Lecouteux, Laurent Besacier. Disentangling ASR and MT Errors in Speech Translation. MT Summit 2017, Sep 2017, Nagoya, Japan. MT Summit 2017 proceedings, 〈http://aamt.info/app-def/S-102/mtsummit/2017/〉. 〈hal-01580877〉

Partager

Métriques

Consultations de la notice

48

Téléchargements de fichiers

38