Lingua Cognito (NLP/Text Processing)
NLP and text processing, with inclusive multimodal systems for education and heritage.
Project overview
Lingua Cognito is the centre's flagship initiative in natural language processing and text processing, co-led by Assoc. Prof. Dr. Norisma Idris and Assoc. Prof. Ts. Dr. Aznul Qalid Md Sabri. Its current focus covers NLP, text processing and inclusive multimodal systems for education and heritage. Assoc. Prof. Idris works on NLP, educational and healthcare AI, and multimodal report generation. Assoc. Prof. Md Sabri works on computer vision, machine learning, AI for healthcare and NLP, including deep reinforcement and transfer learning for abstractive text summarisation. The emphasis on inclusive systems reflects a practical constraint in Malaysian language technology: material that matters for education and cultural heritage is often multilingual, unevenly digitised and spread across text, images and speech, which is precisely the setting multimodal methods are meant to handle.
Research focus
Current focus
Research areas
Leadership
Why this work matters
Language technology tends to work best for the languages and formats already well represented in training data. Education and heritage material in Malaysia frequently is not, which makes it a demanding test of whether a method generalises. Work on inclusive multimodal systems is therefore both an application and a research problem.
Research connections
Publications by the researchers involved, or in the research areas this project spans.
Collaboration
Interested in research collaboration, technical exchange or translational opportunities related to this work?
Discuss a Collaboration