A stochastic model of human-machine interaction for learning dialog strategies

By Esther Levin, Roberto Pieraccini, W. Eckert. 2000

617 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, background): “…et al., 2018; Hixon et al., 2015; Pappu and Rudnicky, 2013), and more commonly in re-inforcement learning settings, where the feedback is a scalar rather than the dialogue messages themselves (Levin et al., 2000; Schatzmann et al., 2006; Rieser and Lemon, 2011; Liu et al., 2018; Hong et al., 2019).”
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models (2015, methodology): “cover conversations on similar topics) then these models can be used to train a user simulator, which can then train the POMDP models discussed earlier (Young et al., 2013; Pietquin and Hastie, 2013; Levin et al., 2000). This would alleviate the expensive and time-consuming task of constructing a la”
Deep Reinforcement Learning for Dialogue Generation (2016, methodology): “Efforts include statistical models such as Markov Decision Processes (MDPs) (Levin et al., 1997; Levin et al., 2000; Walker et al., 2003; Pieraccini et al., 2009), POMDP (Young et al., 2010; Young et al., 2013; Gašic et al., 2013a; Gašic et al., 2014) models, and models that statistically learn…”
Neural Approaches to Conversational AI (2018, neutral): “ or expert-deﬁned rules can be used to set parameters in the stack-update process. Model-based Simulation. Another approach to building user simulators is entirely based on data (Eckert et al., 1997; Levin et al., 2000; Chandramohan et al., 2011). Here, we describe a recent example due to El Asri et”
A Persona-Based Neural Conversation Model (2016, background): “This work follows the line of investigation initiated by Ritter et al. (2011) who treat generation of conversational dialog as a statistical machine translation (SMT) problem.”
A Deep Reinforcement Learning Chatbot (2017, methodology): “pproaches here differ based on how the simulator itself is created or estimated, and whether or not the simulator is also considered an agent, which is trying to optimize its own reward. For example, Levin et al. (2000) tackle the problem of building a ﬂight booking dialogue system. They estimate a ”
Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets (2008, background): “…consisting only of the states of information slots (e.g., destination city ﬁlled with high conﬁdence) in the application (Goddeau and Pineau 2000; Levin, Pieraccini, and Eckert 2000; Singh et al. 2000a, 2000b, 2002; Young 2000; Schefﬂer and Young 2002; Williams, Poupart, and Young 2005a, 2005b;…”
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems (2018, background): “Traditionally, they have been built with several pipelined modules: language understanding, dialog management, knowledge query, and language generation (Williams and Young, 2007; Hori et al., 2009; Lee et al., 2009; Levin et al., 2000; Young et al., 2013).”
End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning (2016, background): “Action selection via RL was originally framed as a Markov decision process (Levin et al., 2000), and later as a partially observable Markov decision process (Young et al., 2013).”
Deploying Lifelong Open-Domain Dialogue Learning (2020, background): “Continual Dialogue Learning Learning from dialogue interaction is common in reinforcement learning settings, where the feedback is a scalar rather than solely the dialogue messages themselves (Levin et al., 2000; Schatzmann et al., 2006; Rieser and Lemon, 2011; Liu and Lane, 2017; Serban et al., 201”
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning (2017, background): “…dialog system into a pipeline, typically including language understanding, dialog state tracking, action selection policy, and language generation (Levin et al., 2000; Singh et al., 2002; Williams and Young, 2007; Williams, 2008; Hori et al., 2009; Lee et al., 2009; Griol et al., 2008; Young et…”
Sample Efficient Deep Reinforcement Learning for Dialogue Systems With Large Action Spaces (2018, methodology): “[17], and SARSA has been applied by Henderson et al.”
The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach (2018, background): “One line of research has focused on learning dialogue systems through simulations using abstract dialogue states and actions (Eckert et al., 1997; Levin et al., 2000; Chung, 2004; Cuay´ahuitl et al., 2005; Georgila et al., 2006; Schatzmann et al., 2007; Heeman, 2009; Traum et al., 2008; Lee &…”
The Hidden Information State Approach to Dialog Management (2007, methodology): “However, conventional POMDPs scale poorly with the size of state and observation space.”
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems (2020, background): “Task-oriented dialogue systems are further classiﬁed into: modularized (Levin et al., 2000; Hori et al., 2009; Lee et al., 2009), retrieval (Henderson et al., 2019; Wu et al., 2020) end-to-end (Bordes and Weston, 2017; Eric et al., 2017a; Eric and Manning, 2017; Reddy et al., 2019; Madotto et al.,…”