Revisiting Multi-Domain Machine Translation - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur Accéder directement au contenu
Article Dans Une Revue Transactions of the Association for Computational Linguistics Année : 2021

Revisiting Multi-Domain Machine Translation

Minh Quang Pham
Josep-Maria Crego
  • Fonction : Auteur
  • PersonId : 1038144
François Yvon

Résumé

When building machine translation systems, one often needs to make the best out of heterogeneous sets of parallel data in training, and to robustly handle inputs from unexpected domains in testing. This multi-domain scenario has attracted a lot of recent work, that fall under the general umbrella of transfer learning. In this study, we revisit multi-domain machine translation, with the aim to formulate the motivations for developing such systems and the associated expectations with respect to performance. Our experiments with a large sample of multi-domain systems show that most of these expectations are hardly met and suggest that further work is needed to better analyze the current behaviour of multi-domain systems and to make them fully hold their promises.
Fichier principal
Vignette du fichier
tacl_a_00351.pdf (286.93 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03159744 , version 1 (04-03-2021)

Identifiants

Citer

Minh Quang Pham, Josep-Maria Crego, François Yvon. Revisiting Multi-Domain Machine Translation. Transactions of the Association for Computational Linguistics, 2021, 9, pp.17-35. ⟨10.1162/tacl_a_00351⟩. ⟨hal-03159744⟩
214 Consultations
166 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More