W02-0703 2000 ) , a memory-based learner . Speech act classification is performed first . Input to
J02-4003 detection . Its typical run time for speech act classification is about 10 speech acts per second
D11-1069 improvement , illustrating that speech act classification is a challenging problem . Representative
W02-0703 classification is performed after speech act classification . The concept sequence classifier
D13-1182 performing speech recognition and speech act classification . Others have investigated visual
D09-1130 Ravi and Kim ( 2007 ) applied speech act classification to detect unanswered questions
N10-1142 actionable tasks in their inbox . As a speech act classification task , however , automatically
W10-1012 last sentence . 3.2 Features for Speech Act Classification We have used six different types
W03-2118 seems like an excellent choice for speech act classification . It was the most accurate classifier
W03-2118 classification task into two subtasks : speech act classification and concept sequence classification
J89-3002 assertive type according to the speech act classification scheme in Searle and Vanderveken
D11-1069 Lampert et al. ( 2006 ) performed speech act classification in email messages following a
W99-0306 game labels , although current speech act classification technology does not yield good
C96-2101 dialogue grammar is needed . Also speech act classification is aban - doned , in favour of
P98-1103 using a surface pattern oriented speech act classification of Seligman et al. ( 1994 ) ,
D11-1069 his belief . 3.2 Features for Speech Act Classification To create speech act classifiers
N10-1142 overlaps significantly with email speech act classification . Their results are difficult
C96-2101 abandoning dialogue grammar and speech act classification , we agree with the common view
P06-3012 more than one code according to speech act classification ( Ballmer and Brennen - stuhl
D12-1009 is a body of work in supervised speech act classification ( Cohen et al. , 2004 ; Bangalore
hide detail