Abstract | ||
---|---|---|
Data-driven techniques have influenced many aspects of speech and language processing. Models derived from data are generally more robust than hand-crafted systems since they better reflect the dis- tributions of the phenomena being modeled. With the availability of large spoken dialog corpora, dialog management can now reap the benefit of data-driven techniques. In this paper, we present our view of structuring human-human dialogs in order to learn mod- els for human-machine dialogs. We present the problems of dialog segmentation and dialog act labeling, develop a model for predict- ing and labeling topic segments and dialog acts and evaluate the model on customer-agent dialogs from a catalog service domain. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ICASSP.2006.1659955 | International Conference on Acoustics, Speech, and Signal Processing |
Keywords | Field | DocType |
interactive systems,natural language interfaces,speech-based user interfaces,catalog service domain,customer-agent dialogs,data-driven techniques,dialog act labeling,dialog management,dialog segmentation,human-machine dialogs,language processing,speech processing,task-oriented human-human dialogs | Dialog act,Dialog box,Speech processing,Speech synthesis,Computer science,Segmentation,Natural language,Dialog system,Artificial intelligence,Natural language processing,Structuring | Conference |
Volume | ISSN | Citations |
1 | 1520-6149 | 3 |
PageRank | References | Authors |
0.43 | 21 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Srinivas Bangalore | 1 | 1319 | 157.37 |
Giuseppe Di Fabbrizio | 2 | 330 | 44.45 |
Amanda J. Stent | 3 | 1094 | 103.35 |