Latent Group Dropout for Multilingual and Multidomain Machine Translation - Laboratoire Interdisciplinaire des Sciences du Numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Latent Group Dropout for Multilingual and Multidomain Machine Translation

Minh Quang Pham
Josep Crego
  • Fonction : Auteur
François Yvon

Résumé

Multidomain and multilingual machine translation often rely on parameter sharing strategies, where large portions of the network are meant to capture the commonalities of the tasks at hand, while smaller parts are reserved to model the peculiarities of a language or a domain. In adapter-based approaches, these strategies are hardcoded in the network architecture, independent of the similarities between tasks. In this work, we propose a new method to better take advantage of these similarities, using a latent-variable model. We also develop new techniques to train this model end-to-end and report experimental results showing that the learned patterns are both meaningful and yield improved translation performance without any increase of the model size.
Fichier principal
Vignette du fichier
2022.findings-naacl.189.pdf (951.15 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03720395 , version 1 (11-07-2022)

Identifiants

  • HAL Id : hal-03720395 , version 1

Citer

Minh Quang Pham, Josep Crego, François Yvon. Latent Group Dropout for Multilingual and Multidomain Machine Translation. Findings of the ACL: NAACL 2022, Association for Computational Linguistics, Jul 2022, Seattle, United States. ⟨hal-03720395⟩
172 Consultations
68 Téléchargements

Partager

Gmail Facebook X LinkedIn More