| D12-1007 | evaluation of simulators without a | dialog manager | . The main approach is to compute |
| D12-1007 | of the user simulator with some | dialog manager | . Schatz - mann et al. ( 2005 |
| D12-1007 | vital for training statistical | dialog managers | in task-oriented domains . These |
| C02-1138 | which is assumed to be output by a | dialog manager | of a spoken dialog system . The |
| D12-1007 | simulator to train a POMDP-based | dialog manager | using a form of reinforcement |
| D12-1007 | frequently used to train statistical | dialog managers | for task-oriented domains . At |
| D14-1223 | additional information for the | dialog manager | by augmenting SLU com - ponents |
| D12-1007 | , 1997 ) . Training effective | dialog managers | should benefit from exposure |
| D14-1223 | parser ( Mori et al. , 2008 ) . The | dialog manager | uses the SLU components to decide |
| A92-1010 | resulting text is returned to the | dialog manager | which presents it to the user |
| C02-1138 | surface generation as follows . The | dialog manager | of Communicator issues a set |
| A92-1010 | Controlling Multimodal Discourse The | dialog manager | is one of the main components |
| D12-1007 | extrinsically by means of the | dialog managers | they are intended to train , |
| C02-1138 | communicative goals for which the | dialog manager | requires realization are matched |
| D12-1007 | been so inextricably linked to | dialog managers | . The most popular method of |
| A92-1010 | meta-dialogs with the user . The | dialog manager | detects misconceptions , i.e. |
| D12-1007 | simulator to train a statistical | dialog manager | and then evaluate the learned |
| D12-1007 | simulator performs well with a certain | dialog manager | , it would perform similarly |
| D12-1007 | evaluate them extrinsically using | dialog managers | . This is circular because we |
| C90-3008 | human-computer interface with a | dialog manager | and a set of automatic semantic |
