Emergent Communication Pretraining for Few-Shot Machine Translation

While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world's languages lack such resources. Hence, we investigate a more rad...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-11
Hauptverfasser:	Li, Yaoyiran, Ponti, Edoardo M, Vulić, Ivan, Korhonen, Anna
Format:	Artikel
Sprache:	eng
Schlagworte:	Adapters Coders Communication Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Learning Evaluation Knowledge management Machine translation Natural language processing Neural networks Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!