Dr. Taha Osman explores using semantic ontologies and LLMs to enhance NLP applications in fields like digital media and social analytics.
Watch the video
Synopsis
The success of Large Language Models (LLM), most notably ChatGPT, has rejuvenated interest in Text Analytics and its applications. LLM-based systems utilise the new generation transformer neural networks that are trained on colossal amounts of text data (GPT-4 processes 100-trillion parameters) to power NLP/Text Analytics applications such as document summary and conversational agents.
Dr Taha Osman has a rich track record in modelling the knowledge embedded in the problem domain into semantic ontologies (knowledge graphs) that have proven effective in improving the classification engines behind information retrieval and sentiment analysis applications.
The research talk will explore the fundamentals of his hybrid knowledgebase – Machine Learning NLP methods and their application to different applications areas including digital media, mineral exploration, and social media analytics.
The talk will also discuss the recent investigation in introducing domain knowledge to boost the classification accuracy of LLMs.
About the speaker
Dr Taha Osman
Dr Taha Osman is a principal lecturer in the Department of Computer Science at the Nottingham Trent University, where he also received his PhD in Fault-Tolerant Distributed Computing. His research interests include the Semantic Web, Knowledge-based Information Extraction, Intelligent Recommender Systems, Linked Open Data, Opinion Mining and Sentiment Analysis , and Arabic NLP Systems
Our events are for adults aged 16 years and over.
BCS is a membership organisation. If you enjoy this event, please consider joining BCS. You’ll be very welcome. You’ll receive access to many exclusive career development tools, an introduction to a thriving professional community and also help us Make IT Good For Society. Join BCS today
This event is brought to you by: Nottingham and Derby branch
