Show simple item record

dc.contributor.authorStolcke, Andreas
dc.contributor.authorCoccaro, Noah
dc.contributor.authorBates, Rebecca
dc.contributor.authorTaylor, Paul
dc.contributor.authorVan Ess-Dykema, Carol
dc.contributor.authorRies, Klaus
dc.contributor.authorShriberg, Elizabeth
dc.contributor.authorJurafsky, Daniel
dc.contributor.authorMartin, Rachel
dc.contributor.authorMeteer, Marie
dc.coverage.spatial36en
dc.date.accessioned2006-05-11T13:07:36Z
dc.date.available2006-05-11T13:07:36Z
dc.date.issued2000-09
dc.identifier.citationComputational Linguistics 26(3) 339-373, 2000.en
dc.identifier.issn0891-2017
dc.identifier.urihttp://dx.doi.org/10.1162/089120100561737
dc.identifier.urihttp://hdl.handle.net/1842/975
dc.description.abstractWe describe a statistical approach for modeling dialogue acts in conversational speech, i.e., speech-act-like units such as STATEMENT, QUESTION, BACKCHANNEL, AGREEMENT, DISAGREEMENT, and APOLOGY. Our model detects and predicts dialogue acts based on lexical, collocational, and prosodic cues, as well as on the discourse coherence of the dialogue act sequence. The dialogue model is based on treating the discourse structure of a conversation as a hidden Markov model and the individual dialogue acts as observations emanating from the model states. Constraints on the likely sequence of dialogue acts are modeled via a dialogue act n-gram. The statistical dialogue grammar is combined with word n-grams, decision trees, and neural networks modeling the idiosyncratic lexical and prosodic manifestations of each dialogue act. We develop a probabilistic integration of speech recognition with dialogue modeling, to improve both speech recognition and dialogue act classification accuracy. Models are trained and evaluated using a large hand-labeled database of 1,155 conversations from the Switchboard corpus of spontaneous human-to-human telephone speech. We achieved good dialogue act labeling accuracy (65% based on errorful, automatically recognized words and prosody, and 71% based on word transcripts, compared to a chance baseline accuracy of 35% and human accuracy of 84%) and a small reduction in word recognition error.en
dc.format.extent2534354 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherMIT Pressen
dc.titleDialogue act modeling for automatic tagging and recognition of conversational speechen
dc.typeArticleen


Files in this item

This item appears in the following Collection(s)

Show simple item record