The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management

Young, Steve; Gašić, Milica; Keizer, Simon; Mairesse, François; Schatzmann, Jost; Thomson, Blaise; Yu, Kai

doi:10.1016/j.csl.2009.04.001

Cited by 378 publications

(257 citation statements)

References 29 publications

Supporting

Mentioning

240

Contrasting

Order By: Relevance

“…More traditional dialog systems typically tease apart dialog management (Young, 2002) from response generation (Stent and Bangalore, 2014), while our holistic approach can be considered a first attempt to accomplish both tasks jointly. While there are previous uses of machine learning for response generation (Walker et al, 2003), dialog state tracking (Young et al, 2010), and user modeling (Georgila et al, 2006), many components of typical dialog systems remain hand-coded: in particular, the labels and attributes defining dialog states. In contrast, the dialog state in our neural network model is completely latent and directly optimized towards end-to-end performance.…”

Section: Related Workmentioning

confidence: 99%

A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

Sordoni¹,

Galley²,

Auli³

et al. 2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

690

566

View full text Add to dashboard Cite

We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances. Our dynamic-context generative models show consistent gains over both context-sensitive and non-context-sensitive Machine Translation and Information Retrieval baselines.

show abstract

Section: Related Workmentioning

confidence: 99%

A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

Sordoni¹,

Galley²,

Auli³

et al. 2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

690

566

View full text Add to dashboard Cite

show abstract

“…In contrast, statistical approaches compute a posterior distribution over many hypotheses for the dialog state, and in general these have been shown to be superior (Horvitz and Paek, 1999;Williams and Young, 2007;Young et al, 2009;Thomson and Young, 2010;Bohus and Rudnicky, 2006;Metallinou et al, 2013;.…”

Section: Introductionmentioning

confidence: 99%

“…Most early work cast dialog state tracking as a generative model in which hidden user goals generate observations in the form of SLU hypotheses (Horvitz and Paek, 1999;Williams and Young, 2007;Young et al, 2009;Thomson and Young, 2010). More recently, discriminatively trained direct models have been applied, and two studies on dialog data from two publicly deployed dialog systems suggest direct models yield better performance (Williams, 2012;Zilka et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

Web-style ranking and SLU combination for dialog state tracking

Williams¹

2014

Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)

108

View full text Add to dashboard Cite

In spoken dialog systems, statistical state tracking aims to improve robustness to speech recognition errors by tracking a posterior distribution over hidden dialog states. This paper introduces two novel methods for this task. First, we explain how state tracking is structurally similar to web-style ranking, enabling mature, powerful ranking algorithms to be applied. Second, we show how to use multiple spoken language understanding engines (SLUs) in state tracking -multiple SLUs can expand the set of dialog states being tracked, and give more information about each, thereby increasing both recall and precision of state tracking. We evaluate on the second Dialog State Tracking Challenge; together these two techniques yield highest accuracy in 2 of 3 tasks, including the most difficult and general task.

show abstract

“…In MDP-based systems, only the most likely dialog state is considered and in this case the primary metric is dialog state accuracy (Bohus and Rudnicky, 2006). In POMDP-based systems, the full distribution is considered and then the shape of the distribution as measured by an L2 norm is equally important (Young et al, 2009). In both cases, good quality state tracking is essential to maintaining good overall system performance.…”

Section: Introductionmentioning

confidence: 99%

Word-Based Dialog State Tracking with Recurrent Neural Networks

Henderson

Thomson²,

Young

2014

Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)

Self Cite

311

292

View full text Add to dashboard Cite

Recently discriminative methods for tracking the state of a spoken dialog have been shown to outperform traditional generative models. This paper presents a new wordbased tracking method which maps directly from the speech recognition results to the dialog state without using an explicit semantic decoder. The method is based on a recurrent neural network structure which is capable of generalising to unseen dialog state hypotheses, and which requires very little feature engineering. The method is evaluated on the second Dialog State Tracking Challenge (DSTC2) corpus and the results demonstrate consistently high performance across all of the metrics.

show abstract

The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management

Cited by 378 publications

References 29 publications

A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

Web-style ranking and SLU combination for dialog state tracking

Word-Based Dialog State Tracking with Recurrent Neural Networks

Contact Info

Product

Resources

About