Multi-Domain Adaptation in Neural Machine Translation with Dynamic Sampling Strategies - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Multi-Domain Adaptation in Neural Machine Translation with Dynamic Sampling Strategies

Minh-Quang Pham
Josep Crego
  • Fonction : Auteur
  • PersonId : 1136018
François Yvon

Résumé

Building effective Neural Machine Translation models often implies accommodating diverse sets of heterogeneous data so as to optimize performance for the domain(s) of interest. Such multi-source / multi-domain adaptation problems are typically approached through instance selection or reweighting strategies, based on a static assessment of the relevance of training instances with respect to the task at hand. In this paper, we study dynamic data selection strategies that are able to automatically re-evaluate the usefulness of data samples in the course of training. Based on the results of multiple experiments, we show that our method offer a generic framework to automatically handle several real-world situations, from multi-source or unsupervised domain adaptation to multidomain learning.
Fichier principal
Vignette du fichier
2022.eamt-1.4.pdf (495.38 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03686763 , version 1 (02-06-2022)

Identifiants

  • HAL Id : hal-03686763 , version 1

Citer

Minh-Quang Pham, Josep Crego, François Yvon. Multi-Domain Adaptation in Neural Machine Translation with Dynamic Sampling Strategies. Conference of the European Association for Machine Translation, European Association for Machine Translation, Jun 2022, Ghent, Belgium. ⟨hal-03686763⟩
80 Consultations
91 Téléchargements

Partager

Gmail Facebook X LinkedIn More