@conference {13705, title = {A lexically-driven algorithm for disfluency detection}, booktitle = {Proceedings of HLT-NAACL 2004: Short Papers}, series = {HLT-NAACL-Short {\textquoteright}04}, year = {2004}, month = {2004///}, pages = {157 - 160}, publisher = {Association for Computational Linguistics}, organization = {Association for Computational Linguistics}, address = {Stroudsburg, PA, USA}, abstract = {This paper describes a transformation-based learning approach to disfluency detection in speech transcripts using primarily lexical features. Our method produces comparable results to two other systems that make heavy use of prosodic features, thus demonstrating that reasonable performance can be achieved without extensive prosodic cues. In addition, we show that it is possible to facilitate the identification of less frequently disfluent discourse markers by taking speaker style into account.}, isbn = {1-932432-24-8}, url = {http://dl.acm.org/citation.cfm?id=1613984.1614024}, author = {Snover,Matthew and Dorr, Bonnie J and Schwartz,Richard} }