Conference Paper Evaluating the Effectiveness of Capsule Neural Network in To...

LLMs attracted considerable interest in the fields of natural language understanding (NLU) & natural language generation (NLG) since their introduction. In contrast, the legacy of Capsule Neural Networks appears to have been largely forgotten amidst all of this excitement.

This project’s objective is to reignite interest in CapsNet by reopening the previously closed studies and conducting a new research into CapsNet’s potential. Here CapsNet is used to classify toxic text by leveraging pretrained BERT embeddings on large multilingual dataset.

In this study, CapsNet was tasked with categorizing toxic text. By comparing the performance of CapsNet to that of other architectures, such as DistilBERT, Vanilla Neural Networks (VNN), and CNN, we were able to achieve an accuracy of 90.44%.

This result highlights the benefits of CapsNet over text data and suggests new ways to enhance their performance so that it is comparable to DistilBERT and other reduced architectures.

Codebase: https://github.com/TashinAhmed/HATE