Resumen

ZHOU, Yujun et al. Hybrid Attention Networks for Chinese Short Text Classification. Comp. y Sist. [online]. 2017, vol.21, n.4, pp.759-769. ISSN 2007-9737.  https://doi.org/10.13053/cys-21-4-2847.

To improve the classification performance for Chinese short text with automatic semantic feature selection, in this paper we propose the Hybrid Attention Networks (HANs) which combines the word- and character-level selective attentions. The model firstly applies RNN and CNN to extract the semantic features of texts. Then it captures class-related attentive representation from word- and character-level features. Finally, all of the features are concatenated and fed into the output layer for classification. Experimental results on 32-class and 5-class datasets show that, our model outperforms multiple baselines by combining not only the word- and character-level features of the texts, but also class-related semantic features by attentive mechanism.

Palabras llave : Chinese short texts; text classification; attentive mechanism; convolutional neural network; recurrent neural network.

        · texto en Inglés     · Inglés ( pdf )