Trigram dialogue control using POMDPs

This paper proposes hybrid dialogue control of both trigram and POMDP dialogue controls by extending our proposed method that uses two approaches: automatically acquiring POMDP structures and rewards for target dialogues through Dynamic Bayesian Networks (DBNs) with a large amount of dialogue data and reflecting action predictive probabilities into the POMDP structures. In this extension, we modify the action predictive probabilities to treat trigram dialogue controls. Experimental results show that the proposed method can treat a trigram dialogue control with robustness for erroneous conditions and can simultaneously maximize trigram probability and the dialogue evaluations obtained from users.