Código QR (código de barras bidimensional)

Pre-Training on Mixed Data for Low-Resource Neural Machine Translation

The pre-training fine-tuning mode has been shown to be effective for low resource neural machine translation. In this mode, pre-training models trained on monolingual data are used to initiate translation models to transfer knowledge from monolingual data into translation models. In recent years, pr...

תיאור מלא

שמור ב:
Principais autores: Wenbo Zhang, Xiao Li, Yating Yang, Rui Dong
פורמט: Artigo
שפה:Inglês
יצא לאור: MDPI AG 2021-03-01
סדרה:Information
נושאים:
neural machine translation
pre-training
low resource
word translation
גישה מקוונת:https://www.mdpi.com/2078-2489/12/3/133
תגים: הוספת תג
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!

פריטים דומים