Persistent information state in a data-centric architecture

2010 IEEE International Conference on Acoustics, Speech and Signal Processing

et al. 2010

We present a call routing application for complex problem solving tasks. Up to date work on call routing has been mainly dealing with call-type classification. In this paper we take call routing further: Initial call classification is done in parallel with a robust statistical Spoken Language Understanding module. This is followed by a dialogue to elicit further taskrelevant details from the user before passing on the call. The dialogue capability also allows us to obtain clarifications of the initial classifier guess. Based on an evaluation, we show that conducting a dialogue significantly improves upon call routing based on call classification alone. We present both subjective and objective evaluation results of the system according to standard metrics on real users.

“…At the implementation level, this balances a lightweight communication protocol downstream with data flowing laterally towards the database. Further details are described in [4].…”

Section: Dialogue System Architecturementioning

confidence: 99%

Section: Task Successmentioning

confidence: 99%

The LUNA Spoken Dialogue System: Beyond utterance classification

Dinarelli

Stepanov

2010 IEEE International Conference on Acoustics, Speech and Signal Processing

et al. 2010

“…If the parameter is accepted, application dependent task rules determine the next parameter to be acquired, resulting in the generation of an appropriate request. See (Varges et al, 2008) for more details.…”

Section: Rule-based Dialogue Managementmentioning

confidence: 99%

Leveraging POMDPs trained with user simulations and rule-based dialogue management in a spoken dialogue system

Proceedings of the SIGDIAL 2009 Conference on the 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue -

Quarteroni

Riccardi

et al. 2009

Self Cite

We have developed a complete spoken dialogue framework that includes rule-based and trainable dialogue managers, speech recognition, spoken language understanding and generation modules, and a comprehensive web visualization interface. We present a spoken dialogue system based on Reinforcement Learning that goes beyond standard rule based models and computes on-line decisions of the best dialogue moves. Bridging the gap between handcrafted (e.g. rule-based) and adaptive (e.g. based on Partially Observable Markov Decision Processes-POMDP) dialogue models, this prototype is able to learn high rewarding policies in a number of dialogue situations.

“…A rule-based dialogue manager was developed as a meaningful comparison to the trained DM, to obtain training data from human-system interaction for the user simulator, and to understand the properties of the domain (Varges et al, 2008). Rulebased dialog management works in two stages: retrieving and preprocessing facts (tuples) taken from a dialogue state database (section 3), and inferencing over those facts to generate a system response.…”

Section: Rule-based Dialogue Managementmentioning

confidence: 99%

Combining POMDPs trained with user simulations and rule-based dialogue management in a spoken dialogue system

Proceedings of the ACL-IJCNLP 2009 Software Demonstrations on - ACL-IJCNLP '09

Quarteroni

Riccardi

et al. 2009

Self Cite

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 moves. The key concept of this work is that we bridge the gap between manually written dialog models (e.g. rule-based) and adaptive computational models such as Partially Observable Markov Decision Processes (POMDP) based dialogue managers.