Social media platforms have become inundated with offensive language. This issue must be addressed for the growth of online social networks (OSNs) and a healthy online environment. While significant research has been devoted to identifying toxic content in major languages like English, this remains an open area of research in the low-resource Pashto language. This study aims to develop an AI model for the automatic detection of offensive textual content in Pashto. To achieve this goal, we have developed a benchmark dataset called the Pashto Offensive Language Dataset (POLD), which comprises tweets collected from Twitter and manually classified into two categories: “offensive” and “not offensive”. To discriminate these two categories, we investigated the classic deep learning classifiers based on neural networks, including CNNs and RNNs, using static word embeddings: Word2Vec, fastText, and GloVe as features. Furthermore, we examined two transfer learning approaches. In the first approach, we fine-tuned the pre-trained multilingual language model, XLM-R, using the POLD dataset, whereas, in the second approach, we trained a monolingual BERT model for Pashto from scratch using a custom-developed text corpus. Pashto BERT was then fine-tuned similarly to XLM-R. The performance of all the deep learning and transformer learning models was evaluated using the POLD dataset. The experimental results demonstrate that our pre-trained Pashto BERT model outperforms the other models, achieving an F1-score of 94.34% and an accuracy of 94.77%.
1 January 2023 in International Journal of Advanced Computer Science and Applications
In recent years, natural language processing (NLP) has transformed numerous domains, becoming a vital area of research. However, the focus of NLP studies has predomi-nantly centered on major languages like English, inadvertently neglecting low-resource languages like Pashto. Pashto, spoken by a population of over 50 million worldwide, remains largely unexplored in NLP research, lacking off-the-shelf resources and tools even for fundamental text-processing tasks. To bridge this gap, this study presents NLPashto, an open-source and publicly accessible NLP toolkit specifically designed for Pashto. The initial version of NLPashto introduces four state-of-the-art models for Spelling Correction, Word Segmentation, Part-of-Speech (POS) Tagging, and Offensive Language Detection. The toolkit also includes essential NLP resources like pre-trained static word embeddings, Word2Vec, fastText, and GloVe. Furthermore, we have pre-trained a monolingual language model for Pashto from scratch, using the Bidirectional Encoder Representations from Transformers (BERT) architecture. For the training and evaluation of all the models, we have developed several benchmark datasets and also included them in the toolkit. Experimental results demonstrate that the models exhibit satisfactory perfor-mance in their respective tasks. This study can be a significant milestone and will hopefully support and speed-up future research in the field of Pashto NLP.
The advancement of artificial intelligence in oral healthcare relies on the availability of large-scale multimodal datasets that capture the complexity of clinical practice. In this paper, we present a comprehensive multimodal dataset, comprising 8775 dental checkups from 4800 patients collected over eight years (2018–2025), with patients ranging from 10 to 90 years of age. The dataset includes 50000 intraoral photographs, 8056 radiographs, and detailed textual records, including diagnoses, treatment plans, and follow-up notes. The data were collected under standard ethical guidelines and annotated for benchmarking. To demonstrate its utility, we fine-tuned state-of-the-art large vision-language models, Qwen-VL 3B and 7B, and evaluated them on two tasks: classification of six oro-dental anomalies and generation of complete diagnostic reports from multimodal inputs. We compared the fine-tuned models with their base counterparts and GPT-4o. The fine-tuned models achieved substantial gains over these baselines, validating the dataset and underscoring its effectiveness in advancing AI-driven oro-dental healthcare solutions. The dataset is publicly available, providing an essential resource for future research in AI dentistry.
About Me
Postdoctoral Researcher at South China University of Technology, China
Postdoctoral Researcher at South China University of Technology, China