Resumen

NAGAR, Ajay; BHASIN, Anmol  y  MATHUR, Gaurav. Text Classification using Gated Fusion of n-gram Features and Semantic Features. Comp. y Sist. [online]. 2019, vol.23, n.3, pp.1015-1020.  Epub 09-Ago-2021. ISSN 2007-9737.  https://doi.org/10.13053/cys-23-3-3278.

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.

Palabras llave : Text classification; convolutional neural network; universal sentence encoder; BiLSTM.

        · texto en Inglés     · Inglés ( pdf )