Show simple item record

dc.contributor.authorHough, Jen_US
dc.contributor.authorPurver, Men_US
dc.contributor.authorSemDial Workshop on the Semantics and Pragmatics of Dialogueen_US
dc.date.accessioned2016-03-14T13:32:50Z
dc.date.issued2013-12en_US
dc.identifier.issn2308-2275en_US
dc.identifier.urihttp://www.illc.uva.nl/semdial/dialdam/papers/HoughPurver_dialdam.pdf.
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/11462
dc.description.abstractThis paper describes a statistical corpus study of self-repairs in the disfluency- annotated Switchboard corpus which examines the time-linear nature of self-repair processing for annotators and listeners in dialogue. The study suggests a strictly lo- cal detection and processing mechanism for self-repairs is sufficient, an advantage currently not used effectively under the bonnet of state-of-the-art automatic dis- fluency processing. We then show how simple local fluency measures using mod- ified language models can be strongly indicative of repair onset detection, and how simple information theoretic mea- sures could characterize different classes of repairen_US
dc.format.extent92 - 101 (9)en_US
dc.language.isoenen_US
dc.publisherUniversity of Amsterdamen_US
dc.subjectStatistical language modellingen_US
dc.subjectfirst-position self- repairsen_US
dc.subjectSwitchboard dis- fluency corpusen_US
dc.subjectdis- fluency processingen_US
dc.titleModelling Expectation in the Self-Repair Processing of Annotat-, um, Listenersen_US
dc.typeConference Proceeding
dc.rights.holder2013. The authors
pubs.author-urlhttp://www.eecs.qmul.ac.uk/%20mpurver/papers/hough-purver13semdial.pdfen_US
pubs.notesNot knownen_US
pubs.publication-statusPublisheden_US
pubs.publisher-urlhttp://www.illc.uva.nl/semdial/dialdam/papers/HoughPurver_dialdam.pdfen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record