This thesis focuses on the problem of scalable optimization of dialogue behaviour in speech-based conversational systems using reinforcement learning. Most previous investigations in dialogue strategy learning have proposed flat reinforcement learning methods, which are more suitable for small-scale spoken dialogue systems. This research formulates the problem in terms of Semi-Markov Decision P...

Over several years, we have developed an approach to spoken dialogue systems that includes rule-based and trainable dialogue managers, spoken language understanding and generation modules, and a comprehensive dialogue system architecture. We present a Reinforcement Learning-based dialogue system that goes beyond standard rule-based models and computes on-line decisions of the best dialogue move...

This study examines the narrative approach of Shahnameh by Ferdowsi based on Bakhtin’s dialogism. The logic of dialogue, a narrative that describes the relationship between different views through dialogue and interaction and considers dialogue as the only way of communication. Dialogism is supplemented by concepts such as "polyphony", "the other voice" and "Carni...

Dialogue acts play an important role in modelling discourse phenomena in several components of modern dialogue systems. Many different features have been so far proposed for dialogue act recognition. In this report, we take a cue-based model approach, and use N grams in utterances in dialogue as cue phrases. In our experiment with the switchboard corpus, we obtained 57.1% classification accurac...

We present a new technique for evaluating spoken dialogue interfaces that allows us to separate the dialogue behavior from the rest of the speech system. By using a dialogue simulator that we have developed, we can gather usability data on the system’s dialogue interaction and behaviors that can guide improvements to the speech interface. Preliminary testing has shown promising results, suggest...

In spoken dialogue systems, robust language processing for spontaneous speech understanding and robust dialogue processing for achieving user goal are inevitable. Previously, research of speech recognition and research of natural language understanding were done independently. At first glance, it seems to be no problem to combine these two technologies, because the purpose of speech recognition...

Quality of Telephone-Based Spoken Dialogue Systems. Quality of Human-Machine Interaction over the Phone.Quality prediction models for telephone-based spoken dialogue systems. Perform to guarantee an acceptable overall quality for the user. In order to.action HHI as one reference for telephonebased humanmachine interaction HMI. The quality of interactions with spoken dialogue systems is difficul...

We present an enhanced method for user feedback in an autonomous learning system that includes a spoken dialogue system to manage the interactions between the users and the system. By means of a rule-based natural language understanding module and a state-based dialogue manager we allow the users to update the preferences learnt by the system from the data obtained from different sensors. The d...

Information about the quality of a Spoken Dialogue System (SDS) is usually used only for comparing SDSs with each other or manually improving the dialogue strategy. This information, however, provides a means for inherently improving the dialogue performance by adapting the Dialogue Manager during the interaction accordingly. For a quality metric to be suitable, it must suffice certain conditio...