Multilingual Auxiliary Task Scaling for Zero-Shot Hate Speech Detection in Low-Resource Languages

The goal of hate speech detection is to filter negative online content aiming at certain groups of people. Due to the easy accessibility and multilinguality of social media platforms, it is crucial to protect everyone which requires building hate speech detection systems for a wide range of languages. However, the available labeled hate speech datasets are limited, making it difficult to build systems for many languages. In this paper we focus on cross-lingual transfer learning to support hate speech detection in low-resource languages, while highlighting label issues across application scenar

Research goal: How does the number of intermediate multilingual auxiliary tasks impact the zero-shot cross-lingual transfer performance of hate speech detection models on low-resource languages in the XTREME-R benchmark, measured by F1-score improvements across domains?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.7/10.