Reinforcement Learning for Spoken Dialogue Systems: Comparing Strengths and Weaknesses for Practical Deployment

By Tim Paek. 2006

69 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Incremental Learning from Scratch for Task-Oriented Dialogue Systems (2019, background): “Such systems work well if all possible combinations of user inputs and conditions are considered in the training stage (Paek and Pieraccini, 2008; Paek, 2006; Wang et al., 2018).”
Synthesis Lectures on Human Language Technologies (2009, background): “Finally, regarding the practical deployment of RL for dialogue systems development, there are a number of issues that need to be addressed (Paek, 2007).”
A Teacher-Student Framework for Maintainable Dialog Manager (2018, methodology): “…there are many methods to train a RL-based dialog manager ef-ﬁciently (Su et al., 2016a, 2017; Lipton et al., 2017; Chang et al., 2017; Chen et al., 2017), the unmaintainable RL-based dialog systems will still be put on the shelf in real-world applications (Paek and Pieraccini, 2008; Paek, 2006).”
Transfer Learning in Deep Reinforcement Learning: A Survey (2020, unknown): “systems [146], Machine Translation [147], to an integration of NLP and Computer Vision tasks, such as Visual Question Answering (VQA) [148], Image Caption [149], etc.”
Automatic Learning and Evaluation of User-Centered Objective Functions for Dialogue System Optimisation (2008, background): “In fact, the reward function is one of the most hand-coded aspects in RL (Paek, 2006).”
An Overview of Natural Language State Representation for Reinforcement Learning (2020, background): “…the state space is a fundamental aspect of RL for dialogue, as it has direct impact on the dynamics of the system, and attention was drawn to the fact that the research community had neither established best practices for modeling the state nor agreed upon domain-independent variables (Paek, 2006).”
Survey on evaluation methods for dialogue systems (2019, methodology): “Thus, partially observable MDPs (POMDP) were adopted, as they introduce the belief state, which models the uncertainty of the current state (Paek 2006; Lemon and Pietquin 2012; Young et al.”