Stopping Active Learning Based on Predicted Change of F Measure for Text Classification
Stopping Active Learning Based on Predicted Change of F Measure for Text Classification
复制标题
DOI：
10.1109/icosc.2019.8665646
复制
发表时间：
2019-01
期刊：
影响因子：
--
通讯作者：
Michael Altschuler;Michael Bloodgood
中科院分区：
文献类型：
--
作者：
Michael Altschuler;Michael Bloodgood
在主动学习过程中，有效的停止方法允许用户限制注释的数量，这是具有成本效益的。在本文中，将引入一种称为“F 测量的预测变化”的新停止方法，该方法尝试为用户提供每次迭代时模型性能变化程度的估计。这种停止方法可以应用于任何基础学习器。该方法对于减少构建文本分类系统时遇到的数据注释瓶颈很有用。
During active learning, an effective stopping method allows users to limit the number of annotations, which is cost effective. In this paper, a new stopping method called Predicted Change of F Measure will be introduced that attempts to provide the users an estimate of how much performance of the model is changing at each iteration. This stopping method can be applied with any base learner. This method is useful for reducing the data annotation bottleneck encountered when building text classification systems.