mlsanityData to 14 Oct 2026

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

arXiv 2210.11359 ↗First posted 20 Oct 2022cs.CLcited by 7

Not on the map. Why?

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.

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

35 of 66 references.

References · 35

  1. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  2. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,254
  3. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  4. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 742
  5. 2019How multilingual is Multilingual BERT?cited by 645
  6. 2021Dynabench: Rethinking Benchmarking in NLPcited by 459
  7. 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
  8. 2019CamemBERT: a Tasty French Language Modelcited by 368
  9. 2020AraBERT: Transformer-based Model for Arabic Language Understandingcited by 362
  10. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 356
  11. 2019Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERTcited by 301
  12. 2018Large Scale Crowdsourcing and Characterization of Twitter Abusive Behaviorcited by 270
23 more
  1. 2020Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learningcited by 249
  2. 2020XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generationcited by 222
  3. 2020Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detectioncited by 221
  4. 2020HateCheck: Functional Tests for Hate Speech Detection Modelscited by 216
  5. 2021XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluationcited by 168
  6. 2019Choosing Transfer Languages for Cross-Lingual Learningcited by 144
  7. 2020Directions in Abusive Language Training Data: Garbage In, Garbage Outcited by 140
  8. 2019Multilingual and Multi-Aspect Hate Speech Analysiscited by 133
  9. 2021XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyondcited by 114
  10. 2020Contextualizing Hate Speech Classifiers with Post-hoc Explanationcited by 84
  11. 2020Gender Bias in Multilingual Embeddings and Cross-Lingual Transfercited by 55
  12. 2020Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languagescited by 52
  13. 2022Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Modelscited by 51
  14. 2020Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysiscited by 45
  15. 2020A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matterscited by 45
  16. 2020What the [MASK]? Making Sense of Language-Specific BERT Modelscited by 44
  17. 2022Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptationcited by 44
  18. 2022Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented Dialogcited by 30
  19. 2021Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalancited by 26
  20. 2020Cross-lingual Zero- and Few-shot Hate Speech Detection Utilising Frozen Transformer Language Models and AXELcited by 23
  21. 2021RoBERTuito: a pre-trained language model for social media text in Spanishcited by 22
  22. 2021Exploring Transformer Based Models to Identify Hate Speech and Offensive Content in English and Indo-Aryan Languagescited by 9
  23. 2020NLPDove at SemEval-2020 Task 12: Improving Offensive Language Detection with Cross-lingual Transfercited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 1; 2026: 1.

7 papers.

  1. 2023SemEval-2023 Task 10: Explainable Detection of Online Sexismcited by 48
  2. 2023Cross-Cultural Transfer Learning for Chinese Offensive Language Detectioncited by 21
  3. 2024The Unseen Targets of Hate -- A Systematic Review of Hateful Communication Datasetscited by 6
  4. 2023Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Datacited by 1
  5. 2024Alternative Speech: Complementary Method to Counter-Narrative for Better Discoursecited by 1
  6. 2025Large Language Models for Toxic Language Detection in Low-Resource Balkan Languagescited by 0
  7. 2026The Cross-Domain Generalization Cost of Offensive Language Detectioncited by 0