What is it about?
Offensive language typically in low-resource language is not common. This study uses Tamil language to detect the offensive pattern with machine learning approaches, typically comparing supervised and unsupervised approaches.
Featured Image
Why is it important?
The findings show that unsupervised approach shows a tremendous performance compared to supervised to detect the offensive pattern in low-resourced language. Nonetheless, unsupervised clustering has shown better accuracy in terms of accuracy compared to human annotated dataset.
Perspectives
I hope that this article provides an insight to researchers on improvising clustering methods with balanced and imbalanced dataset.
Vithya Govindan
University of Malaya
Read the Original
This page is a summary of: Tamil Offensive Language Detection: Supervised versus Unsupervised Learning Approaches, ACM Transactions on Asian and Low-Resource Language Information Processing, December 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3575860.
You can read the full text:
Contributors
The following have contributed to this page
