| Revista: | Computación y sistemas |
| Base de datos: | |
| Número de sistema: | 000560457 |
| ISSN: | 1405-5546 |
| Autores: | Nagar, Ajay1 Bhasin, Anmol1 Mathur, Gaurav1 |
| Instituciones: | 1Samsung R&D Institute India, Bangalore. India |
| Año: | 2019 |
| Periodo: | Jul-Sep |
| Volumen: | 23 |
| Número: | 3 |
| Paginación: | 1015-1020 |
| País: | México |
| Idioma: | Inglés |
| Tipo de documento: | Artículo |
| Resumen en inglés | We introduce a novel method for text classification based on gated fusion of n-gram features and semantic features of the text. The parallel CNN network captures the n-gram relation between the words based on the filter size, primarily short distance multiword relations. Whereas for semantic relationship, universal sentence encoder or BiLSTM is used. Gated fusion is used to combine n-gram and semantic features. The model is evaluated on 4 commonly used benchmark datasets (MR, TREC, AG-News and SUBJ), which includes sentiment analysis and question classification. The proposed method is able to surpass the existing state-of-the-art DNN architectures for text classification on these datasets. |
| Disciplinas: | Ciencias de la computación |
| Palabras clave: | Inteligencia artificial |
| Keyword: | Text classification, Convolutional neural network, Universal sentence encoder, BiLSTM, Artificial intelligence |
| Texto completo: | Texto completo (Ver HTML) Texto completo (Ver PDF) |
