Hybrid Attention Networks for Chinese Short Text Classification



Título del documento: Hybrid Attention Networks for Chinese Short Text Classification
Revista: Computación y Sistemas
Base de datos: PERIÓDICA
Número de sistema: 000423291
ISSN: 1405-5546
Autores: 1
1
1
1
1
1
Instituciones: 1Institute of Automation, Beijing. China
2University of Chinese Academy of Sciences, Beijing. China
3Jiangsu Jinling Science and Technology Group Co., Ltd, Nanjing, Jiangsu. China
Año:
Periodo: Oct-Dic
Volumen: 21
Número: 4
País: México
Idioma: Inglés
Tipo de documento: Artículo
Enfoque: Aplicado, descriptivo
Resumen en inglés 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
Disciplinas: Ciencias de la computación,
Literatura y lingüística
Palabras clave: Lingüística aplicada,
Clasificación de textos,
Redes neuronales recurrentes,
Red neuronal convolucional
Keyword: Applied linguistics,
Text classification,
Convolutional neural network,
Recurrent neural network
Texto completo: Texto completo (Ver HTML) Texto completo (Ver PDF)