C. H. Nakatani and D. R. Traum. Coding discourse structure in dialogue (version 1.0). Technical Report UMIACS-TR-99-03, University of Maryland, 1999.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....by a video mixer into synchronized video clips. 3.2 Data Coding 10 experiment sessions resulted in 10 dialogues per condition (20 in total) transcribed as follows. Coding verbal behaviors: As grounding occurs within a turn, which consists of consecutive utterances by a speaker, following [13] we tokenized a turn into utterance units (UU) corresponding to a single intonational phrase [14] Each UU was categorized using the DAMSL coding scheme [15] In the statistical analysis, we concentrated on the following four categories with regular occurrence in our data: Acknowledgement, ....

Nakatani, C. and D. Traum, Coding discourse structure in dialogue (version 1.0). 1999, University of Maryland.

No context found.

C. H. Nakatani and D. R. Traum. Coding discourse structure in dialogue (version 1.0). Technical Report UMIACS-TR-99-03, University of Maryland, 1999.

....actions or addressing other utterances. These include acceptances of requests (which will create an obligation to perform the requested act) as well as rejections and other moves that won t include such obligations. We will return to these acts in the next section. 3. 2 Grounding Following [6, 33, 24], we treat grounding as occurring in discrete bundles of dialogue introduced information that are added to the common ground together. Common Ground Units (CGUs) are modeled as information stores with state, which can be updated by the performance of the grounding acts from [35, 33] initiate ....

C. H. Nakatani and D. R. Traum. Coding discourse structure in dialogue (version 1.0). Technical Report UMIACS-TR-99-03, University of Maryland, 1999.

....and can be managed with take initiative, holdinitiative, and release initiative actions. These acts can often be signalled by performing (only) appropriate corespeech acts in context, e.g. as proposed by [47, 46] We are not currently considering nonverbal signals of initiative. Following [16, 43, 31], we treat grounding as occurring in discrete bundles of dialogue introduced information that are added to the common ground together. Common Ground Units (CGUs) are modeled as information stores with state, which can be updated by the performance of the grounding acts from [45, 43] initiate, ....

C. H. Nakatani and D. R. Traum. Coding discourse structure in dialogue (version 1.0). Technical Report UMIACS-TR-99-03, University of Maryland, 1999.

....kinds of acts, however. First is related to reliable tagging and computing proper inclusion exclusion of relevant parts of the collaborative action. Finding the right units at which to apply the tags can be a difficult process (see, e.g. discussions in (Discourse Resource Initiative, 1997; Nakatani and Traum, 1999)) This difficulty is compounded when there are multiple acts with different boundaries (e.g. the single agent act and multi agent component performed by a speaker within an utterance) Another issue is the kind of logic that will allow this kind of action will need to be more complex than that ....

Nakatani, C. H. and Traum, D. R. (1999). Coding discourse structure in dialogue (version 1.0). Technical Report UMIACS-TR-99-03, University of Maryland.

.... understanding of the problem, Christine Nakatani David Traum in advance of the workshop came up with a method of tagging dialogues looking at two aspects of discourse structure: one based on addition to common ground, and one based on intentional structure of aspects in the common ground [Nakatani and Traum, 1999]. Participants were asked to prepare for the discussions by using this scheme on several dialogues. Nakatani Traum also co chaired the discussion session. The discussions in the workshop and afterwards are reported later in this brochure by the chairs of the discussion groups. 7 At the last ....

....point for intentional structure, and lacking any compelling counter examples, we decided to put the hypothesis to the test in the coding exercises. 3.2. 1 The Coding Scheme The coding scheme used for pre meeting coding exercises was distributed to the group members prior to coding assignments [ Nakatani and Traum, 1999 ] As mentioned above, this included two levels of coding, common ground units (CGUs) at the meso level, and intentional informational units (IUs) at the macro level. Here we provide a brief summary of these coding schemes. Interested parties are referred to the manual [ Nakatani and Traum, ....

[Article contains additional citation context not shown here]

Christine H. Nakatani and David R. Traum. Coding discourse structure in dialogue (version 1.0). Technical Report UMIACS-TR-99-03, University of Maryland, 1999.

....though, is that it is also possible for an utterance to be only a part of one unit. The grounding acts model has clear (though not necessarily correct) positions with respect to the difficulties with vague and subject to multiple usage. For this reason we used the term Common Ground Unit (CGU) in (Nakatani Traum 1999). 5 No attempt has been made to try to model grounding among groups of larger than two persons. The contribution model explicitly talks about partners, though it was also applied primarily to pairs. Novick, Walton, Ward 1996) adapt the contribution model to larger groups. Next Act In State S ....

Nakatani, C. H., and Traum, D. R. 1999. Coding discourse structure in dialogue (version 1.0). Technical Report UMIACS-TR-99-03, University of Maryland.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC