UvA

One of the common parts of news is to provide the background for a current event, such as the resignation of a Prime Minister. This paper addresses a framework that facilitates semi-automated authoring of explanatory audio-visual news topics in a retrospective style for the domain of politics based on already edited new stories available in the repository of the news corporation. The aim is to facilitate a journalist with an audio-visual body based on which he/she can finalize the explanatory piece. The proposed framework enhances current state of the art video summarization by allowing the combination of different news stories into one coherent explanation about a topic of the current news. The framework introduces techniques that exploit demoscopic data in form of polls for the development of the general story outline; the automatic retrieval of relevant material by using a combination of event templates and automatic news summarization over topic threads; and the generation of the final video by applying a set of trimming rules. Example generations are presented and discussed and an outline of future work is presented.