Text classification problems via BERT embedding method and graph convolutional neural network

TL;DR

This paper introduces a novel approach combining BERT embeddings with graph convolutional neural networks to improve text classification accuracy on datasets like BBC news and IMDB reviews.

Contribution

It presents a new method that integrates BERT embeddings with GCNs for text classification, outperforming traditional machine learning models.

Findings

GCN with BERT embeddings outperforms classical models

The method achieves higher classification accuracy

Experimental results on BBC and IMDB datasets

Abstract

This paper presents the novel way combining the BERT embedding method and the graph convolutional neural network. This combination is employed to solve the text classification problem. Initially, we apply the BERT embedding method to the texts (in the BBC news dataset and the IMDB movie reviews dataset) in order to transform all the texts to numerical vector. Then, the graph convolutional neural network will be applied to these numerical vectors to classify these texts into their ap-propriate classes/labels. Experiments show that the performance of the graph convolutional neural network model is better than the perfor-mances of the combination of the BERT embedding method with clas-sical machine learning models.