UTSA NLP at SemEval-2022 Task 4: An Exploration of Simple Ensembles of Transformers, Convolutional, and Recurrent Neural Networks

TL;DR

This paper explores simple ensemble methods combining transformers, CNNs, and RNNs for detecting patronizing language online, achieving competitive F-scores and providing insights for future improvements.

Contribution

It introduces an effective ensemble approach of multiple neural architectures for detecting condescending language, with detailed analysis and performance results.

Findings

Ensemble of five RoBERTa models achieved F-score of 0.6441 on dev set.

Simple ensemble methods outperform individual models.

Error analysis highlights model limitations and future directions.

Abstract

The act of appearing kind or helpful via the use of but having a feeling of superiority condescending and patronizing language can have have serious mental health implications to those that experience it. Thus, detecting this condescending and patronizing language online can be useful for online moderation systems. Thus, in this manuscript, we describe the system developed by Team UTSA SemEval-2022 Task 4, Detecting Patronizing and Condescending Language. Our approach explores the use of several deep learning architectures including RoBERTa, convolutions neural networks, and Bidirectional Long Short-Term Memory Networks. Furthermore, we explore simple and effective methods to create ensembles of neural network models. Overall, we experimented with several ensemble models and found that the a simple combination of five RoBERTa models achieved an F-score of .6441 on the development dataset and .5745 on the final test dataset. Finally, we also performed a comprehensive error analysis to better understand the limitations of the model and provide ideas for further research.