Monolingual Adapters for Zero-Shot Neural Machine Translation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Monolingual Adapters for Zero-Shot Neural Machine Translation

Résumé

We propose a novel adapter layer formalism for adapting multilingual models. They are more parameter-efficient than existing adapter layers while obtaining as good or better performance. The layers are specific to one language (as opposed to bilingual adapters) allowing to compose them and generalize to unseen language-pairs. In this zero-shot setting, they obtain a median improvement of +2.77 BLEU points over a strong 20-language multilingual Transformer baseline trained on TED talks.
Fichier non déposé

Dates et versions

hal-02962247 , version 1 (09-10-2020)

Identifiants

  • HAL Id : hal-02962247 , version 1

Citer

Jerin Philip, Alexandre Bérard, Laurent Besacier, Matthias Gallé. Monolingual Adapters for Zero-Shot Neural Machine Translation. EMNLP (Empirical Methods for Natural Language Processing), Nov 2020, Virtual, France. ⟨hal-02962247⟩
252 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More