融合多粒度特征和标签语义共现的多标签分类

Multi-label Classification with Multi-granularity and Label Semantic Co-occurrence Features

为了从文本中可以更加准确地分析其蕴含的内容,给人们的生产生活提供建议,在基于深度学习的传统多标签分类方法的基础上,提出一种融合多粒度特征和标签语义共现的多标签分类模型。该模型利用双向长短时记忆网络双向长短时记忆网络(bidirectional long short-term memory network,Bi-LSTM)提取多粒度的文本特征,获得不同层次的文本特征;并通过计算pmi的方式构建标签关系图,利用图卷积网络(graph convolution network,GCN)深入提取标签的隐藏关系,获得具有标签信息的文本表示;最终融合多粒度文本特征,进行多标签文本分类。在AAPD和news数据集上进行实验。结果表明:所提出模型的Micro-F1值分别达到0.704和0.729,验证了模型的有效性。

In order to analyze the content contained in the text more accurately and provide suggestions for people􀆳s production and life,a multi-label classification model that combines multi-granularity features and label semantics on the basis of the traditional multilabel classification method based on deep learning was proposed.Bidirectional long short-term memory network(Bi-LSTM)was used in this model to extract multi-grained text features and obtain text features at different levels.The label diagram was constructed by calculating pmi,and the graph convolution network(GCN)was used to extract hidden relationships of labels and obtain text representation with label information.Finally,multi-granularity text features were fused to carry out multi-label text classification.Experiments were conducted on AAPD and news data sets.The results show that the Micro-F1 values of the proposed model are up to 0.704 and 0.729,respectively,which verifies the effectiveness of the model.