Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages
This addresses the challenge of developing hate speech detection models for hundreds of languages with limited data, though it is incremental in improving existing methods for low-resource settings.
The paper tackled the problem of expanding hate speech detection to under-resourced languages by exploring data-efficient strategies, finding that a small amount of target-language fine-tuning data achieves strong performance with diminishing returns, and that English data can partially substitute for it.
Hate speech is a global phenomenon, but most hate speech datasets so far focus on English-language content. This hinders the development of more effective hate speech detection models in hundreds of languages spoken by billions across the world. More data is needed, but annotating hateful content is expensive, time-consuming and potentially harmful to annotators. To mitigate these issues, we explore data-efficient strategies for expanding hate speech detection into under-resourced languages. In a series of experiments with mono- and multilingual models across five non-English languages, we find that 1) a small amount of target-language fine-tuning data is needed to achieve strong performance, 2) the benefits of using more such data decrease exponentially, and 3) initial fine-tuning on readily-available English data can partially substitute target-language data and improve model generalisability. Based on these findings, we formulate actionable recommendations for hate speech detection in low-resource language settings.