Text Classification
Chapter 4 - 使用 表征类模型（BERT/特征抽取类）进行分类，使用 生成式模型进行分类
归一化详解
解释几种归一化的原理
A robust approach for aspectbased sentiment analysis using deep learning and domain ontologies
Purpose – The purpose of this research study is to improve sentiment analysis (SA) at the aspect level, which is accomplished through two independent goals of aspect term and opinion extraction and subsequent sentiment classification.