Transfer Language Selection for Zero-Shot Cross-Lingual Abusive Language Detection
This work addresses abusive language detection for low-resource languages by leveraging existing data from higher-resource languages, though it is incremental as it builds on cross-lingual transfer learning methods.
The paper tackles the problem of selecting optimal transfer languages for zero-shot cross-lingual abusive language detection, showing that linguistic similarity correlates with classifier performance, enabling better detection in low-resource languages.
We study the selection of transfer languages for automatic abusive language detection. Instead of preparing a dataset for every language, we demonstrate the effectiveness of cross-lingual transfer learning for zero-shot abusive language detection. This way we can use existing data from higher-resource languages to build better detection systems for low-resource languages. Our datasets are from seven different languages from three language families. We measure the distance between the languages using several language similarity measures, especially by quantifying the World Atlas of Language Structures. We show that there is a correlation between linguistic similarity and classifier performance. This discovery allows us to choose an optimal transfer language for zero shot abusive language detection.