ACL Findings2025
Word-Level Detection of Code-Mixed Hate Speech with Multilingual Domain Transfer
Abstract
The exponential growth of offensive language on social media tends to fuel online harassment and challenges detection mechanisms. Hate speech detection is commonly treated as a monolingual or multilingual sentence-level classification task. However, profane language tends to contain code-mixing, a combination of more than one language, which requires a more nuanced detection approach than binary classification. A general lack of available codemixed datasets aggravates the problem. To address this issue, we propose five word-level annotated hate speech datasets, EN and DE from social networks, one subset of the DE-EN Offensive Content Detection Code-Switched Dataset, one DE-EN code-mixed German rap lyrics held-out test set, and a cross-domain heldout test set. We investigate the capacity of fine-tuned German-only, German-English bilingual, and German-English code-mixed token classification XLM-R models to generalize to code-mixed hate speech in German rap lyrics in zero-shot domain transfer as well as across different domains. The results show that bilingual fine-tuning facilitates not only the detection of code-mixed hate speech, but also neologisms, addressing the inherent dynamics of profane language use.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on4
- Unsupervised Cross-lingual Representation Learning at ScaleAlexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary et al.ACL 2020 · 539 citations
- The State of Profanity Obfuscation in Natural Language Processing Scientific PublicationsDebora Nozza, Dirk HovyACL Findings 2023 · 4 citations
- Hateful Word in Context ClassificationSanne Hoeken, Sina Zarrieß, Özge AlaçamEMNLP 2024 · 2 citations
- In-context Mixing (ICM): Code-mixed Prompts for Multilingual LLMsBhavani Shankar, Preethi Jyothi, Pushpak BhattacharyyaACL 2024
Related papers
- Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced LanguagesPaul Röttger, Debora Nozza, Federico Bianchi, Dirk HovyEMNLP 2022 · 16 citations
- Vicinal Risk Minimization for Few-Shot Cross-lingual Transfer in Abusive Language DetectionGretel Liz De la Peña Sarracén, Paolo Rosso, Robert Litschko, Goran Glavas et al.EMNLP 2023 · 2 citations
- Improving the Detection of Multilingual Online Attacks with Rich Social Media Data from SingaporeJanosch Haber, Bertie Vidgen, Matthew Chapman, Vibhor Agarwal et al.ACL 2023 · 4 citations
- HARALD: Augmenting Hate Speech Data Sets with Real DataIlan Tal, Dan VilenchikEMNLP Findings 2022 · 4 citations
- Exploring Methods for Building Dialects-Mandarin Code-Mixing Corpora: A Case Study in Taiwanese HokkienSin-En Lu, Bo-Han Lu, Chao-Yi Lu, Richard Tzong-Han TsaiEMNLP Findings 2022 · 5 citations
