An Empirical Study on Adaptive Inference for Pretrained Language Model

Adaptive inference has been proven to improve bidirectional encoder representations from transformers (BERT)'s inference speed with minimal loss of accuracy. However, current work only focuses on the BERT model and lacks exploration of other pretrained language models (PLMs). Therefore, this ar...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems Jg. 34; H. 8; S. 4321 - 4331
Hauptverfasser:	Liu, Weijie, Zhao, Xin, Zhao, Zhe, Ju, Qi, Yang, Xuefeng, Lu, Wei
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.08.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Acceleration Adaptation models Adaptive inference Benchmarks bidirectional encoder representations from transformers (BERT) Bit error rate Coders Computational modeling distillation FastPLM Inference Inference mechanisms Labels Language Mathematical models pretrained language model (PLM) Task analysis Transformers
ISSN:	2162-237X, 2162-2388, 2162-2388
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!