BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The benefits of a multidimensional approach to dialogue modelling 
 - Harry Bunt\, University of Tilburg
DTSTART:20101116T160000Z
DTEND:20101116T173000Z
UID:TALK27061@talks.cam.ac.uk
CONTACT:Chris Cummins
DESCRIPTION:In this talk I will present a multidimensional approach to the
  interpretation and\ngeneration of utterances in multimodal dialogue\, and
  argue that such an approach\nhas numerous benefits.\n\nWhat is mean by a 
 'multidimensional' approach is that participation in a dialogue\nis viewed
  as being involved in multiple\, parallel activities such as advancing\na 
 dialogue-mediated task or activity\; giving and providing communicative fe
 edback\;\ntaking turns\; monitoring the use of time\; editing one's own an
 d one's partner's\nspeech\, and so on. These various types of activity are
  called 'dimensions'\, and\nthe activities that are performed in each dime
 nsion are called 'dialogue acts.'\nDialogue acts are defined semantically 
 in terms of update operations on the\nparticipants' mental states\; in par
 ticular on their beliefs\, goals\, and\nobligations. This view has been wo
 rked out in considerable detail in the framework\nknown as Dynamic Interpr
 etation Theory (DIT).\n\nOne of the results of analyzing dialogues in the 
 DIT framework has been the\ndevelopment of a fine-grained 10-dimensional t
 axonomy of dialogue act types\,\ncalled the DIT++ taxonomy (http://dit.uvt
 .nl)\, which has been applied in human and\ncomputer recognition\, annotat
 ion\, and generation of dialogue acts.\n\nI will outline the framework of 
 Dynamic Interpretation Theory and the DIT++\ntaxonomy\, and show the benef
 its of this framework for (1) the segmentation of\n(spoken and multimodal)
  dialogue behavior into meaningful units\; (2) the analysis\nand explanati
 on of the phenomenon that dialogue utterances often have more than one\nco
 mmunicative function\; (3) the annotation of spoken and multimodal dialogu
 e with\nsemantic information\; (4) the complex semantics of discourse conn
 ectives\; and (5)\nthe generation of deliberately multifunctional utteranc
 es by a dialogue system.
LOCATION:GR-06/07\, English Faculty Building
END:VEVENT
END:VCALENDAR
