Information state and dialogue management in the TRINDI dialogue move engine toolkit

By Staffan Larsson, David R. Traum. Natural Language Engineering, 2000

606 citations recorded by the source corpus.

We introduce an architecture and toolkit for building dialogue managers currently being developed in the TRINDI project, based on the notions of information state and dialogue move engine. The aim is to provide a framework for experimenting with implementations of different theories of information state, information state update and dialogue control. A number of dialogue managers are currently being built using the toolkit, and we present overviews of two of them. We believe that this framework will make implementation of dialogue processing theories easier, also facilitating comparison of different types of dialogue systems, thus helping to achieve a prerequisite for arriving at a best practice for the development of the dialogue management component of a spoken dialogue system.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/0059e902765146e58542a6716b69e2993793be55

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning (2016, background): “First, action selection may be hand-crafted, as in VoiceXML, AIML, or a number of long-standing research frameworks (Larsson and Traum, 2000; Seneff and Polifroni, 2000).”
Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets (2008, methodology): “For the latter challenge, we exploit the Information State Update (ISU) approach to dialogue systems (Bohlin et al. 1999; Larsson and Traum 2000), which provides the kind of rich and ﬂexible feature-based representations of context that are used with many recent machine learning methods, including…”
Sample-efficient batch reinforcement learning for dialogue management optimization (2011, methodology): “The dialogue state is usually represented efficiently by the Information State paradigm [Larsson and Traum 2000].”
Societal Grounding Is Essential to Meaningful Language Use (2006, methodology): “We use this connection to develop a systematic characterization of societal grounding, and then sketch an architecture for realizing societal grounding within the information-state approach to dialogue management ( Larsson & Traum 2000 ).”
A General, Abstract Model of Incremental Dialogue Processing (2009, methodology): “Lastly, we are now starting to work on connecting the model for incremental processing and grounding of interpretations in previous processing re-sults described here with models of dialogue-level grounding in the information-state update tradition (Larsson and Traum, 2000).”
Neural Approaches to Conversational AI (2018, neutral): “ches There is a huge literature on managing (spoken) dialogue systems. A comprehensive survey is out of the scope of the this chapter. Interested readers are referred to earlier examples (Cole, 1999; Larsson and Traum, 2000; Rich et al., 2001; Bos et al., 2003; Bohus and Rudnicky, 2009), as well as ”
The Hidden Information State Approach to Dialog Management (2007, background): “Firstly, in common with MDPs, the state space of a practical SDS is very large and if represented directly,it would be intractable.”
The Dialog State Tracking Challenge Series: A Review (2016, methodology): “These are covered in detail in Section 3; illustrative examples include hand-crafted rules (Larsson and Traum, 2000; Bohus and Rudnicky, 2003), heuristic scores (Higashinaka et al., 2003), Bayesian networks (Paek and Horvitz, 2000; Williams and Young, 2007), and discriminative models (Bohus and…”
Synthesis Lectures on Human Language Technologies (2009, methodology): “The TrindiKit (Larsson and Traum, 2000) is a Prolog-based toolkit that is used to implement, for example, the Gothenburg Dialogue System (GODIS).”
Using General-Purpose Planning for Action Selection in Human-Robot Interaction (2016, background): “An important direction in interactive systems research has been the development of toolkits that support their construction (Rich and Sidner 1998; Larsson and Traum 2000; Bohus and Rudnicky 2009; Lison 2015).”
Partially observable Markov decision processes for spoken dialog systems (2007, neutral): “The Summary POMDP performs belief monitoring by enumerating all possible user goals, and while this enumeration is reasonable for comparatively simple dialog models such as slot-filling, it is not directly applicable to more complex applications such as those tackled by Information State Update syst”
Machine Learning for Dialog State Tracking: A Review (2015, methodology): “Early spoken dialog systems used hand-crafted rules for DST, keeping a single top hypothesis for each component of the dialog state, often with corresponding confidence scores [6, 7].”