Monitoring AI enhancements in Urdu
Latest Urdu-focused AI updates and research-backed news
Mar 28, 2024NamedEntityRecognition(NER) is a natural language processing task that has been widely explored for different languages in the recent decade but is still an under-researched area for theUrdu...
Open Full NewsOct 29, 2025This study unveils theNamedEntityRecognition(NER) system specifically designed forUrdunews headlines, aimed at bridging crucial linguistic resource gaps. We meticulously developed a comprehensive corpus from diverse news sources, specifically tailored to reflectUrdu'sunique orthographic and morphological characteristics. Our approach incorporates state-of-the-art (SOTA) neural ...
Open Full NewsMar 28, 2024NamedEntityRecognition(NER) is a natural language processing task that has been widely explored for different languages in the recent decade but is still an under-researched area for theUrdulanguage due to its rich morphology and language complexities. Existing state-of-the-art studies onUrduNER use various deep-learning approaches through automatic feature selection using word ...
Open Full NewsThe emergence of multimodal content, particularly text and images on social media, has positioned MultimodalNamedEntityRecognition(MNER) as an increasingly important area ofresearchwithin Natural Language Processing. Despite progress in high-resource languages such as English, MNER remains underexplored for low-resource languages likeUrdu. The primary challenges include the scarcity of ...
Open Full NewsUser's intent detection provides essential cues in query understanding and accurate information retrieval through search engines and task-oriented dialogue systems. Intent detection from user queries is challenging due to short query length and lack of sufficient context. Further, limited prior research in query intent detection has been conducted forUrdu, an under-resourced language. With ...
Open Full NewsWe propose to exploit a pre-trainedUrdu-BERTas a transfer learning model afterfine-tuningits parameters on a newly designedUrducorpus from the Twitter platform.
Open Full NewsFine-tuninga multilingualBERTmodel forUrdusentiment classification, which has been trained on 104 languages, includingUrdu, and is based on aBERTbase with 12 layers, 768 hidden heads, and ...
Open Full NewsApr 15, 2024In particular,fine-tuningis performed onBERTBASE and ELMo usingUrduWikipedia and news articles. Second, a novel generative Data Augmentation (DA) technique replaces Named Entities (NEs) with mask tokens, employing pre-trained masked language models to predict masked tokens, effectively expanding the training dataset.
Open Full NewsIn thispaperwefine-tune three variants of pre-trainedBERTmodels; mBERT, ArBERT1 and roBERTa-urdu-small2 for downstream task of intent detection. We report the results of each intent detection model using four evaluation metrics; precision, recall, accuracy and F1.
Open Full Newshe language policy in the era of artificial intelligence and the role of the same in the case ofUrduand Punjabi inPakistan. A qualitative study design is appropriate since theresearchis centered on the topic of language, power, ideology
Open Full NewsNov 7, 2024NationalUniversityof Science and Technology (NUST), National Information Technology Board (NITB) and Telecom network operator Jazz have signed a Memorandum of Understanding (MOU) to developPakistan'sfirst indigenous Large Language Model (LLM) with focus onUrdu, including datasets for Pashto and Punjabi languages. It is aimed at empowering individuals, businesses, and organizations with ...
Open Full NewsNov 6, 2024VEON announced that Jazz, its digital operator inPakistan, has signed a memorandum of understanding (MoU) with the NationalUniversityof Sciences and Technology (NUST) and the National Information Technology Board (NITB). This collaboration aims to developPakistan'sfirst indigenous Large Language Model (LLM) to serve under-resourced regional languages, supporting digital inclusivity in ...
Open Full News