Promoting extension and reuse in a spoken dialog manager

Hanna, Philip; O'Neill, Ian; Wootton, Craig; McTear, Michael F.

doi:10.1145/1255171.1255173

Cited by 5 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the DM module must choose a system action based on the current state in accordance with a certain policy. Conventional methods [21]- [23] generally handle the dialog processes in a deterministic way. They assume that the system must be in a certain predefined state, and a system action is chosen according to some manually specified rules.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management Through Dynamic Stochastic State Evolution

Lee

2015

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

In this paper, we present a probabilistic framework for goal-driven spoken dialog systems. A new dynamic stochastic state (DS-state) is then defined to characterize the goal set of a dialog state at different stages of the dialog process. Furthermore, an entropy minimization dialog management (EMDM) strategy is also proposed to combine with the DS-states to facilitate a robust and efficient solution in reaching a user's goals. A song-on-demand task, with a total of 38 117 songs and 12 attributes corresponding to each song, is used to test the performance of the proposed approach. In an ideal simulation, assuming no errors, the EMDM strategy is the most efficient goal-seeking method among all tested approaches, returning the correct song within 3.3 dialog turns on average. Furthermore, in a practical scenario, with top five candidates to handle the unavoidable automatic speech recognition (ASR) and natural language understanding (NLU) errors, the results show that only 61.7% of the dialog goals can be successfully obtained in 6.23 dialog turns on average when random questions are asked by the system, whereas if the proposed DS-states are updated with the top five candidates from the SLU output using the proposed EMDM strategy executed at every DS-state, then a 86.7% dialog success rate can be accomplished effectively within 5.17 dialog turns on average. We also demonstrate that entropy-based DM strategies are more efficient than non-entropy based DM. Moreover, using the goal set distributions in EMDM, the results are better than those without them, such as in sate-of-the-art database summary DM.Index Terms-Automatic speech recognition (ASR), dialog management, dialog state modeling, dialog turns, entropy minimization, probabilistic dialog representation, spoken dialog system, spoken language understanding.

show abstract

Section: Introductionmentioning

confidence: 99%

“…They assume that the system must be in a certain predefined state, and a system action is chosen according to some manually specified rules. Many graph-based [21] and frame-based systems [22], [23] are typical examples of these so-called rule-based techniques. They are often effective and easy to implement for simple tasks.…”

Section: Introductionmentioning

confidence: 99%

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management Through Dynamic Stochastic State Evolution

Lee

2015

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

show abstract

“…Second, the DM module must choose a system action based on the current state in accordance with a certain policy. Conventional methods [17]- [19] generally handle the dialog processes in a deterministic way. They assume that the system must be in a certain predefined state, and a system action is chosen according to some manually specified rules.…”

Section: Introductionmentioning

confidence: 99%

“…They assume that the system must be in a certain predefined state, and a system action is chosen according to some manually specified rules. Many graph-based [17] and frame-based systems [18], [19] are typical examples of these so-called rule-based techniques. They are often effective and easy to implement for simple tasks.…”

Section: Introductionmentioning

confidence: 99%

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management through Dynamic Stochastic State Evolution

Wu¹,

Li²,

Lee³

2015

Preprint

View full text Add to dashboard Cite

In this paper, we present a probabilistic framework for goal-driven spoken dialog systems. A new dynamic stochastic state (DS-state) is then defined to characterize the goal set of a dialog state at different stages of the dialog process. Furthermore, an entropy minimization dialog management(EMDM) strategy is also proposed to combine with the DS-states to facilitate a robust and efficient solution in reaching a user's goals. A Song-On-Demand task, with a total of 38117 songs and 12 attributes corresponding to each song, is used to test the performance of the proposed approach. In an ideal simulation, assuming no errors, the EMDM strategy is the most efficient goal-seeking method among all tested approaches, returning the correct song within 3.3 dialog turns on average. Furthermore, in a practical scenario, with top five candidates to handle the unavoidable automatic speech recognition (ASR) and natural language understanding (NLU) errors, the results show that only 61.7% of the dialog goals can be successfully obtained in 6.23 dialog turns on average when random questions are asked by the system, whereas if the proposed DS-states are updated with the top 5 candidates from the SLU output using the proposed EMDM strategy executed at every DS-state, then a 86.7% dialog success rate can be accomplished effectively within 5.17 dialog turns on average. We also demonstrate that entropy-based DM strategies are more efficient than non-entropy based DM. Moreover, using the goal set distributions in EMDM, the results are better than those without them, such as in sate-of-the-art database summary DM.

show abstract

Spoken Dialogue Systems

Jokinen

Hirst

2010

Synthesis Lectures on Human Language Technologies

View full text Add to dashboard Cite

Promoting extension and reuse in a spoken dialog manager

Cited by 5 publications

References 17 publications

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management Through Dynamic Stochastic State Evolution

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management Through Dynamic Stochastic State Evolution

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management through Dynamic Stochastic State Evolution

Spoken Dialogue Systems

Contact Info

Product

Resources

About