AIOU Hosts International Workshop on Multimodal Dataset Development for Pakistani Languages
ISLAMABAD, (APP - UrduPoint / Pakistan Point News - 21st Sep, 2026) Experts at Allama Iqbal Open University (AIOU) emphasized that in the era of Artificial Intelligence (AI), the development of high-quality linguistic datasets is essential for the preservation, documentation, and effective representation of Pakistani languages in modern technologies.
They expressed these views during a one-day international workshop on "Development of Multimodal Datasets for Pakistani Languages," organized by the university. The inaugural session was chaired by Professor Dr Syed Amir Shah, Dean, Faculty of Social Sciences and Humanities.
He stated that:
"The development of standardized multimodal datasets for Pakistani languages would not only help ensure their effective representation in the digital world but also provide a strong foundation for linguistic research, education, and the advancement of language technologies."
He congratulated the Department of English and the Forum for Language Initiatives (FLI) for this initiative, adding that such projects would significantly contribute to aligning Pakistani languages with modern digital requirements.
Fakhruddin Akhunzada, Executive Director of FLI, noted that around 80 languages are spoken in Pakistan, many facing survival challenges. He revealed that data on six Pakistani languages had already been collected under the project, while local communities were also being trained in language documentation and preservation.
Dr Muhammad Kamal Khan, Chairman of the Department of English, shared that multimodal data for Pashto, Punjabi, Hazaragi, Saraiki, and other Pakistani languages has been gathered under the project. He highlighted its potential use in linguistic research and various AI applications.
Dr Maisam Ali from Indiana University, USA, the Principal Investigator of the project, praised the team's efforts in collecting comprehensive linguistic data within a short period using modern research methods. He emphasized the dataset's role in preserving and promoting local languages and integrating them into future AI systems.
Dr Rashida Imran stressed the importance of documenting Pakistani languages and developing standardized multimodal datasets for their preservation and effective representation in modern technologies, including AI. She thanked FLI for this initiative and encouraged collaboration among universities, research institutions, and local communities to safeguard Pakistan’s linguistic heritage and ensure the representation of Pakistani languages in future AI technologies.
The workshop was organized by [...]