Sadeed: Advancing Arabic Diacritization Through Small Language Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913998957445120 |
|---|---|
| author | Aldallal, Zeina Chrouf, Sara Hennara, Khalil Hamed, Mohamed Motaism Hreden, Muhammad AlModhayan, Safwan |
| author_facet | Aldallal, Zeina Chrouf, Sara Hennara, Khalil Hamed, Mohamed Motaism Hreden, Muhammad AlModhayan, Safwan |
| contents | Arabic text diacritization remains a persistent challenge in natural language processing due to the language's morphological richness. In this paper, we introduce Sadeed, a novel approach based on a fine-tuned decoder-only language model adapted from Kuwain 1.5B Hennara et al. [2025], a compact model originally trained on diverse Arabic corpora. Sadeed is fine-tuned on carefully curated, high-quality diacritized datasets, constructed through a rigorous data-cleaning and normalization pipeline. Despite utilizing modest computational resources, Sadeed achieves competitive results compared to proprietary large language models and outperforms traditional models trained on similar domains. Additionally, we highlight key limitations in current benchmarking practices for Arabic diacritization. To address these issues, we introduce SadeedDiac-25, a new benchmark designed to enable fairer and more comprehensive evaluation across diverse text genres and complexity levels. Together, Sadeed and SadeedDiac-25 provide a robust foundation for advancing Arabic NLP applications, including machine translation, text-to-speech, and language learning tools. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_21635 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sadeed: Advancing Arabic Diacritization Through Small Language Model Aldallal, Zeina Chrouf, Sara Hennara, Khalil Hamed, Mohamed Motaism Hreden, Muhammad AlModhayan, Safwan Computation and Language Artificial Intelligence Arabic text diacritization remains a persistent challenge in natural language processing due to the language's morphological richness. In this paper, we introduce Sadeed, a novel approach based on a fine-tuned decoder-only language model adapted from Kuwain 1.5B Hennara et al. [2025], a compact model originally trained on diverse Arabic corpora. Sadeed is fine-tuned on carefully curated, high-quality diacritized datasets, constructed through a rigorous data-cleaning and normalization pipeline. Despite utilizing modest computational resources, Sadeed achieves competitive results compared to proprietary large language models and outperforms traditional models trained on similar domains. Additionally, we highlight key limitations in current benchmarking practices for Arabic diacritization. To address these issues, we introduce SadeedDiac-25, a new benchmark designed to enable fairer and more comprehensive evaluation across diverse text genres and complexity levels. Together, Sadeed and SadeedDiac-25 provide a robust foundation for advancing Arabic NLP applications, including machine translation, text-to-speech, and language learning tools. |
| title | Sadeed: Advancing Arabic Diacritization Through Small Language Model |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2504.21635 |