Method and device for training penalty entity classification model

• Main Author: CHEN KEZHOU
• Format: Patent
• Language: Chinese; English
• Published: 01.12.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The embodiment of the invention provides a method and device for training a penalty entity classification model. The method comprises the steps of performing rule marking on a penalty entity sample ina penalty entity corpus to obtain a first marked punishment entity sample; performing label propagation on the remaining penalty entity samples in the penalty entity corpus by using the first labeledpenalty entity sample to obtain a second labeled penalty entity sample; and training a penalty entity classification model using the first and second labeled penalty entity samples. 本说明书的实施例提供一种用于训练处罚实体分类模型的方法及装置。在该方法中，对处罚实体语料库中的处罚实体样本进行规则打标，得到第一已标注处罚实体样本；使用第一已标注处罚实体样本来对处罚实体语料库中的剩余处罚实体样本执行标签传播，得到第二已标注处罚实体样本；以及使用第一和第二已标注处罚实体样本来训练处罚实体分类模型。