Show simple item record

Proceedings of the the First IEEE/ACM Workshop on Spoken Language Technology (SLT)

dc.contributor.authorHsueh, Pei-Yun
dc.contributor.authorMoore, Johanna D.
dc.date.accessioned2010-11-04T16:13:00Z
dc.date.available2010-11-04T16:13:00Z
dc.date.issued2010-11-04T15:56:25Z
dc.identifier.isbn1-4244-0872-5en
dc.identifier.urihttp://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4123371&tag=1en
dc.identifier.urihttp://hdl.handle.net/1842/4182
dc.description.abstractThis study concerns how to segment a scenario-driven multiparty dialogue and how to label these segments automatically. We apply approaches that have been proposed for identifying topic boundaries at a coarser level to the problem of identifying agenda-based topic boundaries in scenario-based meetings. We also develop conditional models to classify segments into topic classes. Experiments in topic segmentation show that a supervised classification approach that combines lexical and conversational features outperforms the unsupervised lexical chain-based approach, achieving 20% and 12% improvement on segmentating top-level and sub-topic segments respectively. Experiments in topic classification suggest that it is possible to automatically categorize segments into appropriate topic classes given only the transcripts. Training with features selected using the Log Likelihood ratio improves the results by 13.3%.en
dc.language.isoenen
dc.subjectpattern classificationen
dc.subjectspeech processingen
dc.titleAutomatic topic segmentation and labeling in multiparty dialogueen
dc.typeConference Paperen
dc.identifier.doi10.1109/SLT.2006.326826en
rps.titleProceedings of the the First IEEE/ACM Workshop on Spoken Language Technology (SLT)en
dc.extent.noOfPages4en
dc.date.updated2010-11-04T16:13:01Z
dc.date.openingDate2006-12-10
dc.date.closingDate2006-12-13


Files in this item

This item appears in the following Collection(s)

Show simple item record