Automating spoken dialogue management design using machine learning: An industry perspective

By Tim Paek, Roberto Pieraccini. 2008

146 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.

In Artificial Intelligence

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; Wang et al., 2018).”
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (2018, background): “…ambiguity when understanding human language (Williams et al., 2013); the need to integrate third-party services and dialogue context in the decision-making (Traum and Lars-son, 2003; Paek and Pieraccini, 2008); and ﬁnally, the ability to generate natural and engaging responses (Stent et al., 2005).”
The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management (2010, background): “Finally, it should be acknowledged that the philosophy of this statistical approach to dialogue system design has been questioned by some industry-focussed practitioners on the grounds that it is inconsistent with the need to provide guarantees to service providers regarding specific system behaviou”
Optimising a handcrafted dialogue system design (2010, result): “This approach has led to promising results but, as some researchers [2] acknowledge, some obstacles are difficult to overcome (Reinforcement Learning skill prerequisite, simulated users, .”
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).”
SimpleDS: A Simple Deep Reinforcement Learning Dialogue System (2016, background): “This is relevant because the vast majority of previous RL-based dialogue systems make use of carefully engineered features to represent the dialogue state [2].”
Neural Approaches to Conversational AI (2018, unknown): “some of the earlier examples (Cole, 1999; Larsson and Traum, 2000; Rich et al., 2001; Allen et al., 2001; Bos et al., 2003; Bohus and Rudnicky, 2009), as well as excellent surveys like McTear (2002), Paek and Pieraccini (2008), and Young et al. (2013) for more information. Here, we review a small su”
Are We There Yet? Research in Commercial Spoken Dialog Systems (2009, background): “While dialog learning research is developing potential breakthrough technology, commercial deployment cannot yet take advantage of it [5] because of the inherent impracticalities of learning policies from scratch through real user interactions—in fact, research is using simulated users—and the diffi”
POMDP-Based Statistical Spoken Dialog Systems: A Review (2013, background): “In conventional systems, the policy is usually defined by a flow chart with nodes representing states and actions, and arcs representing user inputs [5], [6].”
Adversarial Learning of Task-Oriented Neural Dialog Models (2018, background): “On the other side of the spectrum, Paek and Pieraccini (2008) proposed inferring a reward directly from dialog corpora with inverse reinforcement learning (IRL) (Ng et al., 2000).”