Matches in SemOpenAlex for { <https://semopenalex.org/work/W2034684560> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2034684560 endingPage "916" @default.
- W2034684560 startingPage "903" @default.
- W2034684560 abstract "This paper proposes an incremental sparse Bayesian learning method to allow continuous dialog strategy learning from the interactions with real users. Since conventional reinforcement learning (RL) methods require a huge number of dialogs to reach convergence, it has been essential to use a simulated user in training dialog policies. The disadvantage of this approach is that the trained dialog policies always lag behind the optimal one for live users. In order to tackle this problem, a few studies applying online RL methods to dialog management have emerged and showed very promising results. However, these methods are limited to learning online the weight parameters of the basis functions in the model and so need batch learning on a fixed data set or some heuristics to find appropriate values for other meta parameters such as sparsity-controlling thresholds, basis function parameters, and noise parameters. The proposed method attempts to overcome this limitation to achieve fully incremental and fast dialog strategy learning by adopting a sparse Bayesian learning method for value function approximation. In order to verify the proposed method, three different experimental conditions have been used: artificial data, a simulated user, and real users. The experiment on the artificial data showed that the proposed method successfully learns all the parameters in an incremental manner. Also, the experiment on training and evaluating dialog policies with a simulated user clearly demonstrated that the proposed method is much faster than conventional RL methods. A live user study showed that the dialog strategy learned from real users performed as good as the best past systems, although it slightly underperformed the one trained on simulated dialogs due to the difficulty of user feedback elicitation." @default.
- W2034684560 created "2016-06-24" @default.
- W2034684560 creator A5059051692 @default.
- W2034684560 creator A5077285164 @default.
- W2034684560 date "2012-12-01" @default.
- W2034684560 modified "2023-09-25" @default.
- W2034684560 title "Incremental Sparse Bayesian Method for Online Dialog Strategy Learning" @default.
- W2034684560 cites W1211946649 @default.
- W2034684560 cites W1648445109 @default.
- W2034684560 cites W178897730 @default.
- W2034684560 cites W1963750509 @default.
- W2034684560 cites W2000359198 @default.
- W2034684560 cites W2044696706 @default.
- W2034684560 cites W2046513829 @default.
- W2034684560 cites W2072931156 @default.
- W2034684560 cites W2076337359 @default.
- W2034684560 cites W2101709642 @default.
- W2034684560 cites W2105749772 @default.
- W2034684560 cites W2115101920 @default.
- W2034684560 cites W2154740693 @default.
- W2034684560 cites W2156974606 @default.
- W2034684560 cites W2158984235 @default.
- W2034684560 cites W2162382899 @default.
- W2034684560 cites W2162726731 @default.
- W2034684560 cites W2396394954 @default.
- W2034684560 cites W2438667436 @default.
- W2034684560 cites W2911546748 @default.
- W2034684560 cites W4242606736 @default.
- W2034684560 doi "https://doi.org/10.1109/jstsp.2012.2229963" @default.
- W2034684560 hasPublicationYear "2012" @default.
- W2034684560 type Work @default.
- W2034684560 sameAs 2034684560 @default.
- W2034684560 citedByCount "14" @default.
- W2034684560 countsByYear W20346845602013 @default.
- W2034684560 countsByYear W20346845602014 @default.
- W2034684560 countsByYear W20346845602015 @default.
- W2034684560 countsByYear W20346845602016 @default.
- W2034684560 countsByYear W20346845602017 @default.
- W2034684560 countsByYear W20346845602021 @default.
- W2034684560 crossrefType "journal-article" @default.
- W2034684560 hasAuthorship W2034684560A5059051692 @default.
- W2034684560 hasAuthorship W2034684560A5077285164 @default.
- W2034684560 hasConcept C107673813 @default.
- W2034684560 hasConcept C111919701 @default.
- W2034684560 hasConcept C119857082 @default.
- W2034684560 hasConcept C12426560 @default.
- W2034684560 hasConcept C127705205 @default.
- W2034684560 hasConcept C13280743 @default.
- W2034684560 hasConcept C136764020 @default.
- W2034684560 hasConcept C154945302 @default.
- W2034684560 hasConcept C173853756 @default.
- W2034684560 hasConcept C185798385 @default.
- W2034684560 hasConcept C205649164 @default.
- W2034684560 hasConcept C2524010 @default.
- W2034684560 hasConcept C33923547 @default.
- W2034684560 hasConcept C41008148 @default.
- W2034684560 hasConcept C97541855 @default.
- W2034684560 hasConceptScore W2034684560C107673813 @default.
- W2034684560 hasConceptScore W2034684560C111919701 @default.
- W2034684560 hasConceptScore W2034684560C119857082 @default.
- W2034684560 hasConceptScore W2034684560C12426560 @default.
- W2034684560 hasConceptScore W2034684560C127705205 @default.
- W2034684560 hasConceptScore W2034684560C13280743 @default.
- W2034684560 hasConceptScore W2034684560C136764020 @default.
- W2034684560 hasConceptScore W2034684560C154945302 @default.
- W2034684560 hasConceptScore W2034684560C173853756 @default.
- W2034684560 hasConceptScore W2034684560C185798385 @default.
- W2034684560 hasConceptScore W2034684560C205649164 @default.
- W2034684560 hasConceptScore W2034684560C2524010 @default.
- W2034684560 hasConceptScore W2034684560C33923547 @default.
- W2034684560 hasConceptScore W2034684560C41008148 @default.
- W2034684560 hasConceptScore W2034684560C97541855 @default.
- W2034684560 hasIssue "8" @default.
- W2034684560 hasLocation W20346845601 @default.
- W2034684560 hasOpenAccess W2034684560 @default.
- W2034684560 hasPrimaryLocation W20346845601 @default.
- W2034684560 hasRelatedWork W1485630101 @default.
- W2034684560 hasRelatedWork W1862650538 @default.
- W2034684560 hasRelatedWork W2092896632 @default.
- W2034684560 hasRelatedWork W2143603696 @default.
- W2034684560 hasRelatedWork W2174703168 @default.
- W2034684560 hasRelatedWork W2352008582 @default.
- W2034684560 hasRelatedWork W3074294383 @default.
- W2034684560 hasRelatedWork W4296474751 @default.
- W2034684560 hasRelatedWork W4319083788 @default.
- W2034684560 hasRelatedWork W4372278754 @default.
- W2034684560 hasVolume "6" @default.
- W2034684560 isParatext "false" @default.
- W2034684560 isRetracted "false" @default.
- W2034684560 magId "2034684560" @default.
- W2034684560 workType "article" @default.