Classify Sentence from Multiple Perspectives with Category Expert Attention Network

Attention mechanisms achieve promising performance in text classification. When classifying the sentence into a certain category among multiple candidates, the existing attention utilizes a unified attention weight vector to determine contribution of each word. We observe that it is not accurate enough for a single vector to capture diverse category features of a sentence. In this paper, we propose a Category Expert Attention matrix to extract sentence features from different category perspectives. Each row of the attention matrix represents the unique feature of each category. We evaluate our model on four large scale datasets. Empirical results show that our model outperforms previous baseline methods by a significant margin. Especially on the NLPCC dataset, we achieve new state-of-the-art results. We also conduct visualization experiments to interpret how category expert information analyzes sentences.