| other,17-3-P03-1033,ak | level </term> to the <term> system </term> , <term> | knowledge level | </term> on the <term> target domain </term> and | #4341 Specifically, we set up three dimensions of user models: skill level to the system,knowledge level on the target domain and the degree of hastiness. | |
| other,11-3-P03-1033,ak | </term> of <term> user models </term> : <term> | skill level | </term> to the <term> system </term> , <term> knowledge | #4335 Specifically, we set up three dimensions of user models:skill level to the system, knowledge level on the target domain and the degree of hastiness. | |
| other,0-6-P03-1033,ak | </term> for all <term> dimensions </term> . <term> | Dialogue strategies | </term> based on the <term> user modeling </term> | #4382 We obtained reasonable classification accuracy for all dimensions.Dialogue strategies based on the user modeling are implemented in Kyoto city bus information system that has been developed at our laboratory. | |
| other,7-5-P03-1033,ak | classification accuracy </term> for all <term> | dimensions | </term> . <term> Dialogue strategies </term> | #4380 We obtained reasonable classification accuracy for alldimensions. | |
| tech,3-1-P03-1033,ak | effective . We address appropriate <term> | user modeling | </term> in order to generate <term> cooperative | #4284 We address appropriateuser modeling in order to generate cooperative responses to each user in spoken dialogue systems. | |
| tech,8-4-P03-1033,ak | </term> are automatically derived by <term> | decision tree learning | </term> using real <term> dialogue data </term> | #4361 Moreover, the models are automatically derived bydecision tree learning using real dialogue data collected by the system. | |
| other,24-7-P03-1033,ak | the <term> dialogue duration </term> for <term> | skilled users | </term> . This paper presents an <term> unsupervised | #4429 Experimental evaluation shows that the cooperative responses adaptive to individual users serve as good guidance for novice users without increasing the dialogue duration forskilled users. | |
| other,16-7-P03-1033,ak | users </term> serve as good guidance for <term> | novice users | </term> without increasing the <term> dialogue | #4421 Experimental evaluation shows that the cooperative responses adaptive to individual users serve as good guidance fornovice users without increasing the dialogue duration for skilled users. | |
| other,9-1-P03-1033,ak | modeling </term> in order to generate <term> | cooperative responses | </term> to each user in <term> spoken dialogue | #4290 We address appropriate user modeling in order to generatecooperative responses to each user in spoken dialogue systems. | |
| tech,15-1-P03-1033,ak | cooperative responses </term> to each user in <term> | spoken dialogue systems | </term> . Unlike previous studies that focus | #4296 We address appropriate user modeling in order to generate cooperative responses to each user inspoken dialogue systems. | |
| other,27-3-P03-1033,ak | target domain </term> and the degree of <term> | hastiness | </term> . Moreover , the <term> models </term> | #4351 Specifically, we set up three dimensions of user models: skill level to the system, knowledge level on the target domain and the degree ofhastiness. | |
| model,8-3-P03-1033,ak | up three <term> dimensions </term> of <term> | user models | </term> : <term> skill level </term> to the <term> | #4332 Specifically, we set up three dimensions ofuser models: skill level to the system, knowledge level on the target domain and the degree of hastiness. | |
| other,13-2-P03-1033,ak | knowledge </term> or typical kinds of <term> | users | </term> , the <term> user model </term> we propose | #4313 Unlike previous studies that focus on user's knowledge or typical kinds ofusers, the user model we propose is more comprehensive. | |
| other,6-2-P03-1033,ak | Unlike previous studies that focus on <term> | user 's knowledge | </term> or typical kinds of <term> users </term> | #4306 Unlike previous studies that focus onuser 's knowledge or typical kinds of users, the user model we propose is more comprehensive. | |
| lr,13-4-P03-1033,ak | decision tree learning </term> using real <term> | dialogue data | </term> collected by the <term> system </term> | #4366 Moreover, the models are automatically derived by decision tree learning using realdialogue data collected by the system. | |
| measure(ment),3-5-P03-1033,ak | system </term> . We obtained reasonable <term> | classification accuracy | </term> for all <term> dimensions </term> . <term> | #4376 We obtained reasonableclassification accuracy for all dimensions. | |
| model,3-4-P03-1033,ak | <term> hastiness </term> . Moreover , the <term> | models | </term> are automatically derived by <term> | #4356 Moreover, themodels are automatically derived by decision tree learning using real dialogue data collected by the system. | |
| model,16-2-P03-1033,ak | typical kinds of <term> users </term> , the <term> | user model | </term> we propose is more comprehensive | #4316 Unlike previous studies that focus on user's knowledge or typical kinds of users, theuser model we propose is more comprehensive. | |
| tech,18-4-P03-1033,ak | dialogue data </term> collected by the <term> | system | </term> . We obtained reasonable <term> classification | #4371 Moreover, the models are automatically derived by decision tree learning using real dialogue data collected by thesystem. | |
| other,21-7-P03-1033,ak | users </term> without increasing the <term> | dialogue duration | </term> for <term> skilled users </term> . This | #4426 Experimental evaluation shows that the cooperative responses adaptive to individual users serve as good guidance for novice users without increasing thedialogue duration for skilled users. |
