mlsanityData to 14 Oct 2026

Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models

arXiv 2210.13029 ↗First posted 24 Oct 2022cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Zero-shot cross-lingual transfer learning has been shown to be highly challenging for tasks involving a lot of linguistic specificities or when a cultural gap is present between languages, such as in hate speech detection. In this paper, we highlight this limitation for hate speech detection in several domains and languages using strict experimental settings. Then, we propose to train on multilingual auxiliary tasks -- sentiment analysis, named entity recognition, and tasks relying on syntactic information -- to improve zero-shot transfer of hate speech detection models across languages. We show how hate speech detection models benefit from a cross-lingual knowledge proxy brought by auxiliary tasks fine-tuning and highlight these tasks' positive impact on bridging the hate speech linguistic and cultural gap between languages.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 28 of its 59 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

28 of 59 references.

References · 28

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  4. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  5. 2017Automated Hate Speech Detection and the Problem of Offensive Languagecited by 736
  6. 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
  7. 2020Universal Dependencies v2: An Evergrowing Multilingual Treebank Collectioncited by 271
  8. 2020HateCheck: Functional Tests for Hate Speech Detection Modelscited by 216
  9. 2018Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Taskscited by 215
  10. 2019SemEval-2017 Task 4: Sentiment Analysis in Twittercited by 210
  11. 2020Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?cited by 127
  12. 2020Contextualizing Hate Speech Classifiers with Post-hoc Explanationcited by 84
16 more
  1. 2020Multilingual Offensive Language Identification with Cross-lingual Embeddingscited by 71
  2. 2021Towards generalisable hate speech detection: a review on obstacles and solutionscited by 66
  3. 2022Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Modelscited by 51
  4. 2020Massive Choice, Ample Tasks (MaChAmp): A Toolkit for Multi-task Learning in NLPcited by 50
  5. 2021From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understandingcited by 43
  6. 2020English Intermediate-Task Training Improves Zero-Shot Cross-Lingual Transfer Toocited by 39
  7. 2021Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokenscited by 27
  8. 2020Cross-lingual Zero- and Few-shot Hate Speech Detection Utilising Frozen Transformer Language Models and AXELcited by 23
  9. 2019Zero-Resource Cross-Lingual Named Entity Recognitioncited by 18
  10. 2020Treebanking User-Generated Content: a UD Based Overview of Guidelines, Corpora and Unified Recommendationscited by 13
  11. 2021Multi-Task Learning with Sentiment, Emotion, and Target Detection to Recognize Hate Speech and Offensive Languagecited by 12
  12. 2021Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?cited by 11
  13. 2022Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysiscited by 9
  14. 2021A cost-benefit analysis of cross-lingual transfer methodscited by 7
  15. 2018Bleaching Text: Abstract Features for Cross-lingual Gender Predictioncited by 6
  16. 2020Enhancing deep neural networks with morphological informationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 4; 2026: 1.

10 papers.

  1. 2024Cloaked Classifiers: Pseudonymization Strategies on Sensitive Classification Taskscited by 3
  2. 2024Beyond Dataset Creation: Critical View of Annotation Variation and Bias Probing of a Dataset for Online Radical Content Detectioncited by 3
  3. 2024Common Ground, Diverse Roots: The Difficulty of Classifying Common Examples in Spanish Varietiescited by 3
  4. 2025Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Studycited by 3
  5. 2025IYKYK: Using language models to decode extremist cryptolectscited by 3
  6. 2024Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challengescited by 2
  7. 2025Add Noise, Tasks, or Layers? MaiNLP at the VarDial 2025 Shared Task on Norwegian Dialectal Slot and Intent Detectioncited by 2
  8. 2023Evaluating the Effectiveness of Natural Language Inference for Hate Speech Detection in Languages with Limited Labeled Datacited by 1
  9. 2025Multi-lingual Functional Evaluation for Large Language Modelscited by 1
  10. 2026Multilingual Hate Speech Detection and Counterspeech Generation: A Comprehensive Survey and Practical Guidecited by 1