The purpose of this task is to develop models for automatic text detoxification, transforming toxic language into non-toxic language. Despite regulations in various countries and platforms, abusive speech remains a challenge. This task addresses text detoxification in nine languages: English, Spanish, German, Chinese, Arabic, Hindi, Ukrainian, Russian, and Amharic.
Publication
Dementieva et al. (2024). Overview of the Multilingual Text Detoxification Task at PAN 2024. Experimental IR Meets Multilinguality, Multimodality, and Interaction. CLEF 2024. Lecture Notes in Computer Science, volume 14612
Language
Spanish
English
Arabic
Deuch
Hindi
Ukrainian
Chinese
NLP topic
Dataset
Year
2024
Publication link
Ranking metric
Joint score
Task results
| System | joint Sort ascending |
|---|---|
| Team SmurfCat | 0.5620 |
| lmeribal | 0.5550 |
| erehulka | 0.4970 |
| mareksuppa | 0.4920 |
| nikita.sushko | 0.4800 |
