Abstract | ||
---|---|---|
We are interested in the problem of understanding human conversation structure in the context of human-machine and human-human interaction. We present a statistical methodology for detecting the structure of spoken dialogs based on a generative model learned using decision trees. To evaluate our approach we have used the LUNA corpora, collected from real users engaged in problem solving tasks. The results of the evaluation show that automatic segmentation of spoken dialogs is very effective not only with models built using separately human-machine dialogs or human-human dialogs, but it is also possible to infer the task-related structure of human-human dialogs with a model learned using only human-machine dialogs. |
Year | Venue | Keywords |
---|---|---|
2009 | INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5 | Domain Knowledge Acquisition, Spoken Dialog Systems, Dialog Structure Annotation |
Field | DocType | Citations |
Dialog box,Decision tree,Spoken dialog systems,Annotation,Conversation,Domain knowledge,Computer science,Segmentation,Speech recognition,Natural language processing,Artificial intelligence,Generative model | Conference | 5 |
PageRank | References | Authors |
0.44 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
David Griol | 1 | 223 | 49.82 |
Giuseppe Riccardi | 2 | 1046 | 101.15 |
Emilio Sanchis | 3 | 231 | 35.82 |