VERBA VOLANT (from the Latin proverb “Verba volant, scripta manent”, “spoken words fly away, written words remain”) will prototype the application of Natural Language Processing (NLP) techniques to subtitled or closed-captioned videos for journalistic purposes. VERBA will aid European journalists and researchers analyze captions from diverse video sources, such as TV broadcasters and YouTube channels, enabling them to leverage the informational value contained in the vast and fast-growing corpus of quality video subtitles and captions.
Video transcriptions are an underutilized resource by journalists and media researchers, despite the fact that finding information in (and extracting data from) text is much more efficient than watching a video. VERBA VOLANT will bring to the surface the growing corpus of transcripts and provide NLP features in an easy-to-use and convenient tool, enabling journalists and newsrooms to access a whole new kind of information.
Google serves cookies to analyse traffic to this site. Information about your use of our site is shared with Google for that purpose. Find out more.