N06-1027 special characteristics involved in human conversations , messages within a thread are
N06-1027 quantitative study to analyze human conversation focus in the context of online
A97-1010 Number of Inter-Utterances In human conversation , most of the repetition repairs
J81-4002 User-Supplied Changes In normal human conversation , once something is said , it
J88-1011 solved . Referent identification in human conversation is performed both by describing
I05-2016 intended actions . In case of human conversations , a speaker usually interrupts
E87-1030 Abstract Referent identification in human conversation is performed both by describing
J88-3002 to directly query the user . In human conversation this seems to happen frequently
J81-4002 rather than spoken as is normal in human conversations . This simplifies low-level processing
N06-1027 trustworthiness , and speech act analysis of human conversations with feature - oriented link
C90-3062 Repair in Human Interaction In human conversation there are continual implicit
D15-1284 computers to understand humor in human conversations and adapt behavior accordingly
A00-2037 more typical of mixedinitiative human conversation . In this way , we hoped to understand
J91-2004 interruptions are so important in human conversation , if we want to build natural
J91-2004 consequences for HCI . After all , human conversation is spoken , whereas HCI , to
J90-1015 language . In contrast , human -- human conversations are characterized by unpredictability
N06-1027 be considered a special case of human conversation , and since we have huge repositories
H90-1004 strong foreign accent , music or human conversations in the background , tone noise
D09-1035 hearer , systems that analyze human conversations need to be able to extract both
N06-1027 discussion is a special case of human conversation , where people may express their
hide detail