Deep Learning Models for Multilingual Hate Speech Detection
This work addresses the challenge of hate speech detection for low-resource languages, providing an efficient solution and baselines, though it is incremental as it applies existing methods to new multilingual data.
The paper tackled the problem of multilingual hate speech detection by analyzing data in 9 languages from 16 sources, finding that simple models like LASER with logistic regression perform best in low-resource settings, while BERT-based models excel in high-resource settings, with zero-shot classification achieving good results for languages like Italian and Portuguese.
Hate speech detection is a challenging problem with most of the datasets available in only one language: English. In this paper, we conduct a large scale analysis of multilingual hate speech in 9 languages from 16 different sources. We observe that in low resource setting, simple models such as LASER embedding with logistic regression performs the best, while in high resource setting BERT based models perform better. In case of zero-shot classification, languages such as Italian and Portuguese achieve good results. Our proposed framework could be used as an efficient solution for low-resource languages. These models could also act as good baselines for future multilingual hate speech detection tasks. We have made our code and experimental settings public for other researchers at https://github.com/punyajoy/DE-LIMIT.