Large-Scale News Classification using BERT Language Model: Spark NLP Approach

TL;DR

This paper evaluates the performance of BERT-based models for large-scale news classification, comparing accuracy and training efficiency with and without Spark NLP, highlighting trade-offs between computational resources and accuracy.

Contribution

It demonstrates the impact of using Spark NLP pipelines on BERT's accuracy and training time in large-scale news classification tasks.

Findings

BERT without Spark NLP achieves higher accuracy (0.9187) than with Spark NLP (0.8444).

Using Spark NLP reduces training time by 62.9%.

Accuracy drops by only 5.7% when using Spark NLP, compared to significant time savings.

Abstract

The rise of big data analytics on top of NLP increases the computational burden for text processing at scale. The problems faced in NLP are very high dimensional text, so it takes a high computation resource. The MapReduce allows parallelization of large computations and can improve the efficiency of text processing. This research aims to study the effect of big data processing on NLP tasks based on a deep learning approach. We classify a big text of news topics with fine-tuning BERT used pre-trained models. Five pre-trained models with a different number of parameters were used in this study. To measure the efficiency of this method, we compared the performance of the BERT with the pipelines from Spark NLP. The result shows that BERT without Spark NLP gives higher accuracy compared to BERT with Spark NLP. The accuracy average and training time of all models using BERT is 0.9187 and 35 minutes while using BERT with Spark NLP pipeline is 0.8444 and 9 minutes. The bigger model will take more computation resources and need a longer time to complete the tasks. However, the accuracy of BERT with Spark NLP only decreased by an average of 5.7%, while the training time was reduced significantly by 62.9% compared to BERT without Spark NLP.