Incorporating keyword extraction and attention for multi-label text classification

Abstract

As one of the fundamental tasks in natural language processing, Multi-Label Text Classification (MLTC) is used to mark one or more relevant labels for a given text from a large set of labels. Existing MLTC methods have increasingly focused on improving classification effectiveness by fusing the correlations of labels. Still, the research suffers from difficulties in comprehensively extracting text features and distinguishing similar labels. This paper proposed a multi-label text classification model based on keyword extraction and attention mechanism. The model proposed using keywords to represent labels, adopting both self-attention and interactive attention mechanisms (between labels and text) to extract text features and create text vectors. Finally, fusing text vectors as the classifier’s input. Experiments were conducted on two public datasets and a self-built dataset of illegal advertisements. The experimental results showed that the keyword-based label representation approach proposed in this paper can better obtain label semantics, avoid noise and improve the performance of the multi-label text classification.