A Chinese Text Classification Method With Low Hardware Requirement Based on Improved Model Concatenation

TL;DR

This paper proposes a low-hardware Chinese text classification model that combines five sub-models, achieving higher accuracy than existing ensemble methods while requiring less hardware than BERT-based models.

Contribution

It introduces an improved concatenation-based model integrating multiple sub-models for efficient Chinese text classification with low hardware needs.

Findings

Model accuracy is 2% higher than existing ensemble methods.

Hardware requirements are significantly lower than BERT-based models.

The approach effectively balances performance and resource consumption.

Abstract

In order to improve the accuracy performance of Chinese text classification models with low hardware requirements, an improved concatenation-based model is designed in this paper, which is a concatenation of 5 different sub-models, including TextCNN, LSTM, and Bi-LSTM. Compared with the existing ensemble learning method, for a text classification mission, this model's accuracy is 2% higher. Meanwhile, the hardware requirements of this model are much lower than the BERT-based model.