The Hidden Information State Approach to Dialog Management

By Susannah Young, Jost Schatzmann, Karl Weilhammer, Hui Ye. 2007

149 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Social Psychology

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 Social Psychology

Citations in the corpus

Dynamic Dialogue Policy for Continual Reinforcement Learning (2022, background): “This hidden information state, according to Young et al. (2007), should consist of the following information: the predicted user action, the predicted user goal and a representation of the dialogue history.”
Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems (2009, methodology): “In total we utilise 7 different baselines (B1-B7), which correspond to single branches in our policy space (see Figure 1): B1: RECOMMEND only, e.g. (Young et al., 2007) B2: COMPARE only, e.g. (Henderson et al., 2008) B3: SUMMARY only, e.g. (Polifroni and Walker, 2008) B4: SUMMARY followed by…”
Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models (2019, background): “Prior RL research in modular dialog management has focused on policy optimization over hand-crafted action spaces in task-oriented domains (Walker, 2000; Young et al., 2007).”
POMDP-Based Statistical Spoken Dialog Systems: A Review (2013, methodology): “bination strategies [23]–[26]; 2) the factored Bayesian network approach [22],”
Partially observable Markov decision processes for spoken dialog systems (2007, unknown): “In e ﬀ ect, these rules form an ontology of the application domain and they enable user goals to be expressed in a top-down manner which directly reﬂects the order in which sub-topics are typically visited in conversation (Young et al., 2006).”
Dynamic Dialogue Policy Transformer for Continual Reinforcement Learning (2022, background): “This hidden information state, according to Young et al. (2007), should consist of the following information: the predicted user action, the predicted user goal and a representation of the dialogue history.”
The Dialog State Tracking Challenge Series: A Review (2016, methodology): “This limitation has led to two approximations: maintaining a “beam” of only the most likely members of s (Young et al., 2007; DeVault and Stone, 2007; DeVault, 2008; Kim et al., 2008; Henderson and Lemon, 2008; Mehta et al., 2010; Williams, 2010; Raux and Ma, 2011; Gasic and Young, 2011), or…”
Agenda-Based User Simulation for Bootstrapping a POMDP Dialogue System (2007, methodology): “The Hidden Information State (HIS) model is the ﬁrst trainable and scalable implementation of a statistical spoken dialog system based on the Partially-Observable Markov Decision Process (POMDP) model of dialogue (Young, 2006; Young et al., 2007; Williams and Young, 2007).”
Modeling Multi-Action Policy for Task-Oriented Dialogues (2019, methodology): “, 2005, 2008) and reinforcement learning (RL) approaches (Walker, 2000; Young et al., 2007; Gasic and Young, 2014; Williams et al., 2017b; Su et al., 2017) have been adopted”
The best of both worlds: unifying conventional dialog systems and POMDPs (2008, methodology): “, b(s) = p(s|a, o, b) – and there are methods for doing this efficiently and/or approximately [6, 7].”
Survey on evaluation methods for dialogue systems (2019, methodology): “Generative methods have been widely used to manage this task, for example, dynamic Bayesian network (DBN) along with a beam search (Young et al. 2007).”
Integrating expert knowledge into POMDP optimization for spoken dialog systems (2008, methodology): “, b(s) = p(s|a, o, b) – and there are methods for doing this efficiently and/or approximately (Young et al. 2006; Williams 2007).”
The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management (2010, methodology): “The HIS system has been described in outline in a number of conference papers (Young, 2006; Young et al., 2007; Gašić et al., 2008).”