Short text classification based on bidirectional TCN and attention mechanism

Abstract

The context-related semantic information of the text in the traditional short text classification algorithms are not fully captured, a text classification model based on bidirectional temporal convolutional network and attention mechanism (BTCA) was proposed. Multi-layer dilated convolution was used to increase the receptive field and better capture long distance dependent information. At the same time, attention mechanism was used to increase the attention to the local key feature in the text, and the bidirectional temporal convolution network was used to extract contextual multi-scale semantic information to enrich semantics, the problem of sparse short text features was solved to a certain extent, and text classification effect was improved. The public corpus of the THUCNews was used to conduct a comparative experiment. It is pointed out that effect of short text classification is improved by using BTCA model, with an accuracy rate of 91.47%, which is better than commonly used models.