Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2603.05057 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917316043735040 |
|---|---|
| author | Arshad, Inayat Saleem, Fajar Hussain, Ijaz |
| author_facet | Arshad, Inayat Saleem, Fajar Hussain, Ijaz |
| contents | Urdu toxic span detection remains limited because most existing systems rely on sentence-level classification and fail to identify the specific toxic spans within those text. It is further exacerbated by the multiple factors i.e. lack of token-level annotated resources, linguistic complexity of Urdu, frequent code-switching, informal expressions, and rich morphological variations. In this research, we propose MUTEX: a multilingual transformer combined with conditional random fields (CRF) for Urdu toxic span detection framework that uses manually annotated token-level toxic span dataset to improve performance and interpretability. MUTEX uses XLM RoBERTa with CRF layer to perform sequence labeling and is tested on multi-domain data extracted from social media, online news, and YouTube reviews using token-level F1 to evaluate fine-grained span detection. The results indicate that MUTEX achieves 60% token-level F1 score that is the first supervised baseline for Urdu toxic span detection. Further examination reveals that transformer-based models are more effective at implicitly capturing the contextual toxicity and are able to address the issues of code-switching and morphological variation than other models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05057 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MUTEX: Leveraging Multilingual Transformers and Conditional Random Fields for Enhanced Urdu Toxic Span Detection Arshad, Inayat Saleem, Fajar Hussain, Ijaz Computation and Language Artificial Intelligence Urdu toxic span detection remains limited because most existing systems rely on sentence-level classification and fail to identify the specific toxic spans within those text. It is further exacerbated by the multiple factors i.e. lack of token-level annotated resources, linguistic complexity of Urdu, frequent code-switching, informal expressions, and rich morphological variations. In this research, we propose MUTEX: a multilingual transformer combined with conditional random fields (CRF) for Urdu toxic span detection framework that uses manually annotated token-level toxic span dataset to improve performance and interpretability. MUTEX uses XLM RoBERTa with CRF layer to perform sequence labeling and is tested on multi-domain data extracted from social media, online news, and YouTube reviews using token-level F1 to evaluate fine-grained span detection. The results indicate that MUTEX achieves 60% token-level F1 score that is the first supervised baseline for Urdu toxic span detection. Further examination reveals that transformer-based models are more effective at implicitly capturing the contextual toxicity and are able to address the issues of code-switching and morphological variation than other models. |
| title | MUTEX: Leveraging Multilingual Transformers and Conditional Random Fields for Enhanced Urdu Toxic Span Detection |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.05057 |