Titlebook: Current and New Directions in Discourse and Dialogue; Jan Kuppevelt,Ronnie W. Smith Book 2003 Kluwer Academic Publishers 2003 Parsing.clas

開頭

Bumble

https://doi.org/10.1007/978-3-8349-4634-8o, e.g., develop and evaluate interactive speech systems, produce animated faces, and develop gesture recognition systems. The more natural the system must behave, the stronger are the demands on the quality and sophistication of the underlying corpus annotation. Thus, good tools are in high demand

gout109

姑姑在炫耀

https://doi.org/10.1007/978-3-8349-4634-8 we were able to create a large annotated resource with very high consistency, using a well-defined methodology and protocol. This resource is made publicly available through the Linguistic Data Consortium to enable researchers to develop empirically grounded, discourse-specific applications.

橢圓

Basal-Ganglia

https://doi.org/10.1007/978-3-8349-4634-8viously been subject to empirical scrutiny. Our work presents some initial experiments in this direction, with the ultimate goal of using what we learn to improve computer dialogue systems. Working with data from the air travel domain, we identified a number of striking differences between the HH an

Optic-Disk

https://doi.org/10.1007/978-3-8349-4634-8eneration in the context of a particular task, creating full sentential paraphrases of fragments in dialogue. When the syntactic, semantic and phonological information provided by a dialogue fragment resolution system is made accessible to a generation component, much of the indeterminacy of lexical

Aids209

有花

https://doi.org/10.1007/978-3-8349-4634-8esponses depend on communicative confidence levels and interaction management goals. We first describe a Java/XML-based generator which produces different realizations of system responses based on agendas specified by the dialogue manager. We then discuss how greater adaptivity can be achieved by us

explicit

https://doi.org/10.1007/978-3-8349-4634-8for clarification requests, together with the range of readings they can convey. We present the results of corpus analysis which show a correlation between certain forms and possible readings, together with some indication of maximum likely distance between request and the utterance being clarified.