Semantic Tagging and Text Classification for Archives and Content Systems
Many archives and content production systems suffer from a lack of comprehensive content metadata. This presentation describes work to overcome this using automated text tagging and classification tools which can be applied to text documents, video subtitles or speech-to-text transcripts.
Chris Newell is a Lead Technologist at BBC R&D. He has worked on metadata in the broadcasting industry for many years and contributed to DVB, ID3 and TV-Anytime standards. His current research concerns Natural Language Processing and AI.