NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework

Proceedings of the 39th International Conference on Machine Learning, PMLR 162:25438-25451, 2022 Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM,...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Yao, Xingcheng, Zheng, Yanan, Yang, Xiaocong, Yang, Zhilin
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!