11 search results - page 1 / 3 » Automatic Learning and Evaluation of User-Centered Objective... |
LREC
2008
13 years 6 months ago
2008
The ultimate goal when building dialogue systems is to satisfy the needs of real users, but quality assurance for dialogue strategies is a non-trivial problem. The applied evaluat...
CSL
2012
Springer
12 years 7 days ago
2012
Springer
Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estim...
ACL
1998
13 years 5 months ago
1998
This paper describes a novel method by which a dialogue agent can learn to choose an optimal dialogue strategy. While it is widely agreed that dialogue strategies should be formul...
ML
2006
ACM
13 years 4 months ago
2006
ACM
Most game programs have a large number of parameters that are crucial for their performance. While tuning these parameters by hand is rather difficult, efficient and easy to use ge...
DAGSTUHL
1994
13 years 5 months ago
1994
Functionality-based recognition systems recognize objects at the category level by reasoning about how well the objects support the expected function. Such systems naturally assoc...