Deep Learning Method with Attention for Extreme Multi-label Text Classification

Extreme multi-label text classification (XMTC), the problem of finding the most relevant label subset of each document from hundreds or even millions labels, has been a practical and important problem since the boom of big data. Significant progress has been made in recent years by the development of machine learning methods. However, although deep learning method has beaten traditional method in other related areas, it has no clear advantage in XMTC when we consider the performance of prediction. In order to improve the performance of deep learning method for Extreme multi-label text classification, we propose a novel feature extraction method to better explore the text space. Specifically, we build the model consisting of attention mechanism, convolutional neural network and recurrent neural network to extract multi-view features. Extensive experiments on four public available datasets show that our method achieves better performance than several strong baselines, including traditional methods and deep learning methods.