2006 Presentations (Communicative Events)

Story Segmentation of Broadcast News in English, Mandarin and Arabic

Hirschberg, Julia Bell; Rosenberg, Andrew

In this paper, we present results from a Broadcast News story segmentation system developed for the SRI NIGHTINGALE system operating on English, Arabic and Mandarin news shows to provide input to subsequent question-answering processes. Using a rule-induction algorithm with automatically extracted acoustic and lexical features, we report success rates that are competitive with state-of-the-art systems on each input language. We further demonstrate that features useful for English and Mandarin are not discriminative for Arabic.