Controlling Utterance Length in NMT-based Word Segmentation with Attention - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Controlling Utterance Length in NMT-based Word Segmentation with Attention

Résumé

One of the basic tasks of computational language documentation (CLD) is to identify word boundaries in an unsegmented phonemic stream. While several unsupervised monolingual word segmentation algorithms exist in the literature, they are challenged in real-world CLD settings by the small amount of available data. A possible remedy is to take advantage of glosses or translation in a foreign, well-resourced, language, which often exist for such data. In this paper, we explore and compare ways to exploit neural machine translation models to perform unsupervised boundary detection with bilingual information, notably introducing a new loss function for jointly learning alignment and segmentation. We experiment with an actual under-resourced language, Mboshi, and show that these techniques can effectively control the output segmentation length.
Fichier principal
Vignette du fichier
IWSLT2019_paper_5.pdf (544.71 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02343206 , version 1 (02-11-2019)

Identifiants

  • HAL Id : hal-02343206 , version 1

Citer

Pierre Godard, Laurent Besacier, François Yvon. Controlling Utterance Length in NMT-based Word Segmentation with Attention. International Workshop on Spoken Language Translation, Nov 2019, Hong-Kong, China. ⟨hal-02343206⟩
95 Consultations
61 Téléchargements

Partager

Gmail Facebook X LinkedIn More