# Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages

arXiv: https://arxiv.org/abs/2210.11359 · HTML: https://mlsanity.com/paper/2210.11359/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 66 references that are in the map.
- First posted on arXiv 20 Oct 2022.

## Builds on (most cited first, 30 of 35)

- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Dynabench: Rethinking Benchmarking in NLP](https://mlsanity.com/paper/2104.14337/) (2021)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [CamemBERT: a Tasty French Language Model](https://mlsanity.com/paper/1911.03894/) (2019)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning](https://mlsanity.com/paper/2002.05651/) (2020)
- [XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation](https://mlsanity.com/paper/2004.01401/) (2020)
- [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://mlsanity.com/paper/2012.15761/) (2020)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation](https://mlsanity.com/paper/2104.07412/) (2021)
- [Choosing Transfer Languages for Cross-Lingual Learning](https://mlsanity.com/paper/1905.12688/) (2019)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [Multilingual and Multi-Aspect Hate Speech Analysis](https://mlsanity.com/paper/1908.11049/) (2019)
- [XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond](https://mlsanity.com/paper/2104.12250/) (2021)
- [Contextualizing Hate Speech Classifiers with Post-hoc Explanation](https://mlsanity.com/paper/2005.02439/) (2020)
- [Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer](https://mlsanity.com/paper/2005.00699/) (2020)
- [Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages](https://mlsanity.com/paper/2010.03179/) (2020)
- [Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models](https://mlsanity.com/paper/2206.09917/) (2022)
- [Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis](https://mlsanity.com/paper/2010.04543/) (2020)
- [A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters](https://mlsanity.com/paper/2012.15682/) (2020)
- [What the [MASK]? Making Sense of Language-Specific BERT Models](https://mlsanity.com/paper/2003.02912/) (2020)
- [Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation](https://mlsanity.com/paper/2203.09435/) (2022)
- [Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialog](https://mlsanity.com/paper/2205.10400/) (2022)

## Built on by (most cited first, 7 of 7)

- [SemEval-2023 Task 10: Explainable Detection of Online Sexism](https://mlsanity.com/paper/2303.04222/) (2023)
- [Cross-Cultural Transfer Learning for Chinese Offensive Language Detection](https://mlsanity.com/paper/2303.17927/) (2023)
- [The Unseen Targets of Hate -- A Systematic Review of Hateful Communication Datasets](https://mlsanity.com/paper/2405.08562/) (2024)
- [Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Data](https://mlsanity.com/paper/2306.03722/) (2023)
- [Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse](https://mlsanity.com/paper/2401.14616/) (2024)
- [Large Language Models for Toxic Language Detection in Low-Resource Balkan Languages](https://mlsanity.com/paper/2506.09992/) (2025)
- [The Cross-Domain Generalization Cost of Offensive Language Detection](https://mlsanity.com/paper/2607.23512/) (2026)

## Abstract (arXiv)

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.