Abstract
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.- Anthology ID:
- 2022.emnlp-main.383
- Volume:
- Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5674–5691
- Language:
- URL:
- https://aclanthology.org/2022.emnlp-main.383
- DOI:
- Cite (ACL):
- Paul Röttger, Debora Nozza, Federico Bianchi, and Dirk Hovy. 2022. Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5674–5691, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
- Cite (Informal):
- Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages (Röttger et al., EMNLP 2022)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2022.emnlp-main.383.pdf