Paper: Story Segmentation Of Broadcast News In English Mandarin And Arabic

ACL ID N06-2032
Title Story Segmentation Of Broadcast News In English Mandarin And Arabic
Venue Human Language Technologies
Session Short Paper
Year 2006
Authors

In this paper, we present results from a Broadcast News story segmentation sys- tem developed for the SRI NIGHTIN- GALE system operating on English, Ara- bic and Mandarin news shows to provide input to subsequent question-answering processes. Using a rule-induction algo- rithm with automatically extracted acous- tic 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 use- ful for English and Mandarin are not dis- criminative for Arabic.