This paper focuses on a comparison study between the traditional deep learning techniques like LSTMs and GRUs with the latest state-of-the-art transformers for the task of classifying a comment based on its toxicity. Specifically, four different deep learning models are built, implemented and trained on a standard dataset for comparing the performance of the models. The models that are explored and compared are Bi-directional LSTMs, GRUs, Bi-directional LSTMs with CNNs and Transformers (with pre-trained RoBERTa weights).
Track: Artificial Intelligence
Published in: 11th Annual International Conference on Industrial Engineering and Operations Management, Singapore, Singapore
Publisher: IEOM Society International
Date of Conference: March 7
-11
, 2021
ISBN: 978-1-7923-6124-1
ISSN/E-ISSN: 2169-8767