Reinforcement Learning for Adaptive Dialogue Systems - A Data-driven Methodology for Dialogue Management and Natural Language Generation

By Verena Rieser, Oliver Lemon. 2011

149 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Reinforcement Learning

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

In Reinforcement Learning

Citations in the corpus

Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, methodology): “Regardless of when feedback is requested, existing methods typically require accompanying scalar rewards or adherence to particular templates or structure to ensure that the feedback is usable by the model (Rieser and Lemon, 2011; Zhang et al., 2017; Liu et al., 2018).”
Dialog-based Language Learning (2016, neutral): “C L ] 1 8 M ay 2 01 6”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “Recent advances in dialogue management have involved using reinforcement learning methods to learn a dialogue management policy (Singh et al., 2002; Scheffler and Young, 2002; Pietquin et al., 2011; Rieser and Lemon, 2011; Peng et al., 2017; Fazel-Zarandi et al., 2017).”
Deal or No Deal? End-to-End Learning of Negotiation Dialogues (2017, methodology): “RL has been widely used to improve dialogue managers, which manage transitions between dialogue states (Singh et al., 2002; Pietquin et al., 2011; Rieser and Lemon, 2011; Gašic et al., 2013; Fatemi et al., 2016).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “…utterances in dialogue systems (e.g., Walker et al., 2007a; Rieser & Lemon, 2009; Dethlefs, 2014) is another application of nlg, but typically it is closely related to dialogue management, so that management and realisation policies are sometimes learned in tandem (e.g., Rieser & Lemon, 2011b).”
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”
I love your chain mail! Making knights smile in a fantasy game world: Open-domain goal-oriented dialogue agents (2019, background): “Earlier work focused on labeled state representations, slot filling mechanisms and dialogue managers (Rieser & Lemon, 2011), and more recent work has shifted to an end-to-end approach (Bordes et al., 2017), in line with chit-chat models, but still the two sets of tasks are rarely considered…”
MAKING KNIGHTS SMILE IN A FANTASY GAME WORLD (2019, background): “Earlier work focused on labeled state representations, slot filling mechanisms and dialogue managers (Rieser & Lemon, 2011), and more recent work has shifted to an end-to-end approach (Bordes et al., 2017), in line with chit-chat models, but still the two sets of tasks are rarely considered…”
A review of evaluation techniques for social dialogue systems (2017, methodology): “Traditional dialogue systems [8, 10] tend to be task-orientated for a limited domain and evaluation methods of such systems have been much researched (see [1] for an overview).”
Natural Language Generation as Incremental Planning Under Uncertainty: Adaptive Information Presentation for Statistical Dialogue Systems (2014, methodology): “The chosen features indicate that users’ ratings are influenced by higher level and lower dialogue level features: Users like to be focused on a small set of database hits (where #DBhits ranges over [1-100]), which will enable them to choose an item (valueUserReaction), while keeping the IP utteranc”
Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots (2021, background): “…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; Ser-ban et al., 2017), which is most common in a goal-oriented setting where completion of the goal can…”