A C T UNE : Uncertainty-Aware Active Self-Training for Active Fine-Tuning of Pretrained Language Models
Yinhan Liu, Myle Ott, Naman Goyal, Jing-Fei Du, M. Joshi, Dan-Qi Chen, Omer Levy, Mike Lewis, Katerina Margatina, Loïc Barrault, Giorgos Vernikos, Loïc Barrault, Subhabrata Mukherjee, A. Awadallah, Fabian Pedregosa, Gaël Varoquaux, V. Michel, B. Thirion, Olivier, M. Blondel, P. Prettenhofer, Alexander Ratner, Stephen H. Bach, Henry R. Ehrenberg, Thomas Wolf, Lysandre Debut, Julien Victor Sanh, Clement Chaumond, Anthony Delangue, Pier-339 Moi and 33 others
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
No abstract is available from our sources. Use “Read paper” to view it.
TL;DRA C T UNE is developed, a new 008 framework that improves the label efficiency 009 of active PLM fine-tuning by unleashing the 010 power of unlabeled data via self training by unleashing the 010 power of unlabeled data via self training. (Semantic Scholar)