Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation

We propose a new training objective named order-agnostic cross entropy (OaXE) for fully non-autoregressive translation (NAT) models. OaXE improves the standard cross-entropy loss to ameliorate the effect of word reordering, which is a common source of the critical multimodality problem in NAT. Concr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Du, Cunxiao, Tu, Zhaopeng, Jiang, Jing
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!