A Label-Enhanced Text Classification Model

Abstract

In the field of text classification, most of the previous work only uses one-hot labels, ignoring the correlations between labels. The paper proposes a novel label-enhanced text classification model, which utilizes the semantic correlation between sentences and category labels in the Natural Language Processing (NLP) classification task to integrate label information. We measure the similarity between instance and the category with the correlations among the labels. We test the proposed model on text classification tasks in two levels: text classification (document level) and sentiment analysis (sentence level). Experimental results show that the label-enhanced text classification model achieves great performance in multiple text classification tasks. In addition, experiment results on the unbalanced datasets show that our model is able to mitigate the impact of unbalanced data in classification tasks.