Abstract | ||
---|---|---|
Data-driven techniques have been used for many computational linguistics tasks. Models derived from data are generally more robust than hand-crafted systems since they better reect the distribution of the phenomena being modeled. With the availability of large corpora of spo- ken dialog, dialog management is now reaping the benets of data-driven tech- niques. In this paper, we compare two ap- proaches to modeling subtask structure in dialog: a chunk-based model of subdialog sequences, and a parse-based, or hierarchi- cal, model. We evaluate these models us- ing customer agent dialogs from a catalog service domain. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/TASL.2008.2001102 | IEEE Transactions on Audio, Speech, and Language Processing |
Keywords | Field | DocType |
games,natural language processing,speech recognition,speech,hidden markov models,predictive models | Dialog box,Spoken dialog,Computer science,Computational linguistics,Dialog system,Natural language processing,Dialog management,Artificial intelligence,Machine learning | Journal |
Volume | Issue | ISSN |
16 | 7 | 1558-7916 |
Citations | PageRank | References |
26 | 1.15 | 42 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Srinivas Bangalore | 1 | 26 | 1.15 |
Giuseppe Di Fabbrizio | 2 | 330 | 44.45 |
Amanda Stent | 3 | 82 | 3.22 |