ANTS— a complete system for automatic news programme annotation

This article describes an integrated system for the automatic annotation of television news programmes named ANTS (Automatic Newscast Transcription System). It consists of several analysis components, integrated within a unified architecture. Users have the possibility of accessing a large daily-growing database of news stories from the main national channels - all identified, categorised and published in a fully automatic way. The system identifies story boundaries, extracts texts from spoken content, classifies stories by subject and links external relevant information coming from the web. The system's performance has been evaluated in a real-life scenario by a panel of professional users inside RAI. The strength of the approach behind ANTS is its ability to integrate several heterogeneous tools in a performant and ready-for- production environment. ANTS is capable of elaborating many hours of material per day, without significant service drops and with sufficiently good accuracy for industrial deployment in large broadcasting facilities.