AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models-猫眼课题宝

DOI：

10.18653/v1/2022.naacl-main.102

发表时间：

2022

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Yue Yu;Lingkai Kong;Jieyu Zhang;Rongzhi Zhang;Chao Zhang

虽然微调预训练语言模型（PLM）在许多NLP任务中表现出色，但它依赖于过多的标记数据。最近，研究人员采取主动微调，以提高PLM微调的标签效率，但这种类型的现有方法通常忽略了潜在的未标记的数据。我们开发了AcTune，这是一个新的框架，通过自我训练释放未标记数据的力量，提高了主动PLM微调的标签效率。AcTune基于不确定性在数据注释和模型自训练之间切换：选择高不确定性的未标记样本进行注释，而来自低不确定性区域的样本用于模型自训练。此外，我们设计了（1）一个区域感知的采样策略，以避免查询注释时的冗余样本，以及（2）一个基于动量的内存库，以动态聚合模型的伪标签，以抑制自训练中的标签噪声。在6个文本分类数据集上的实验表明，AcTune优于最强的主动学习和自训练基线，并将PLM微调的标签效率平均提高了56.2%。我们的实现可以在https://github.com/yueyu1030/actune上获得。

Although fine-tuning pre-trained language models (PLMs) renders strong performance in many NLP tasks, it relies on excessive labeled data. Recently, researchers have resorted to active fine-tuning for enhancing the label efficiency of PLM fine-tuning, but existing methods of this type usually ignore the potential of unlabeled data. We develop AcTune, a new framework that improves the label efficiency of active PLM fine-tuning by unleashing the power of unlabeled data via self-training. AcTune switches between data annotation and model self-training based on uncertainty: the unlabeled samples of high-uncertainty are selected for annotation, while the ones from low-uncertainty regions are used for model self-training. Additionally, we design (1) a region-aware sampling strategy to avoid redundant samples when querying annotations and (2) a momentum-based memory bank to dynamically aggregate the model’s pseudo labels to suppress label noise in self-training. Experiments on 6 text classification datasets show that AcTune outperforms the strongest active learning and self-training baselines and improves the label efficiency of PLM fine-tuning by 56.2% on average. Our implementation is available at https://github.com/yueyu1030/actune.

AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language Models

文献摘要

相似文献