One Source, Two Targets: Challenges and Rewards of Dual Decoding - Traitement du Langage Parlé Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

One Source, Two Targets: Challenges and Rewards of Dual Decoding

Jitao Xu
  • Fonction : Auteur
  • PersonId : 184998
  • IdHAL : xujitao
François Yvon

Résumé

Machine translation is generally understood as generating one target text from an input source document. In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the other. As we discuss, such a device serves several practical purposes, from multi-target machine translation to the generation of controlled variations of the target text. We present an analysis of possible implementations of dual decoding, and experiment with four applications. Viewing the problem from multiple angles allows us to better highlight the challenges of dual decoding and to also thoroughly analyze the benefits of generating matched, rather than independent, translations.
Fichier principal
Vignette du fichier
emnlp2021.pdf (324.07 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03345478 , version 1 (15-09-2021)

Identifiants

  • HAL Id : hal-03345478 , version 1

Citer

Jitao Xu, François Yvon. One Source, Two Targets: Challenges and Rewards of Dual Decoding. Conference on Empirical Methods in Natural Language Processing, Nov 2021, Online and Punta Cana, Dominican Republic. ⟨hal-03345478⟩
73 Consultations
123 Téléchargements

Partager

Gmail Facebook X LinkedIn More