ANSES: Automatic News Summarization and Extraction System
"Watch the news while I was away and tell me what happened."
This project combines a Video scene change algorithm, with the current text segmentation and summarization techniques to build an automatic news summarization and extraction system.
Television broadcast news are captured both in Video/Audio format with the accompanying subtitles in text format. News stories are identified, extracted from the video, and summarized in a short paragraph which reduces the amount of information into a manageable size. Individual news video clips can be retrieved effectively by a combination of video and text, using a reversed indexed search engine to provide distilled information such as a summarized version of the orginal text and highlights important key words in the text.
Quick start
This guide is to help you quickly try out the application, a more detailed
user guide is available through the menu above.
The application is straightforward to use. It opens displaying the latest
available news, split into stories. Each story is displayed in a panel with
three components:
- video key frames across the top, with a link to play the video
- key words down the left hand side, these are categorised into organisations, people, locations and dates
- a central panel with a text summary of the story, its date and a link to the full story.
At the top of the main page there are drop down boxes to allow you to select
and display previous days news. Just below the date selection area there is a
link to the search page. On the search page you can query the news archive by
text and date range. The text query searches the key words extracted from each
story.
Application
This link -- ANSES -- will open the application in a new browser.Papers
M Pickering, L Wong and S Rüger: ANSES: Summarisation of news video. Int'l Conf on Image and Video Retrieval (CIVR, Urbana-Champaign, IL), Springer LNCS 2728, pp 425–434, Jul 2003