Discourse Cues for Broadcast News Segmentation

This paper describes the design and application of time-enhanced, finite state models of discourse cues to the automated segmentation of broadcast news. We describe our analysis of a broadcast news corpus, the design of a discourse cue based story segmentor that builds upon information extraction techniques, and finally its computational implementation and evaluation in the Broadcast News Navigator (BNN) to support video news browsing, retrieval, and summarization.

• Type: Conference
• Year: 1998
• Where: ACL
• Authors: Mark T. Maybury
• Keywords: ACL 1998, ACL 2007, Cue Based Story, Discourse Cue, Finite State Models