2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2019
DOI: 10.1109/asru46091.2019.9003871
|View full text |Cite
|
Sign up to set email alerts
|

Robust Belief State Space Representation for Statistical Dialogue Managers Using Deep Autoencoders

Abstract: Statistical Dialogue Systems (SDS) have proved their humongous potential over the past few years. However, the lack of efficient and robust representations of the belief state (BS) space refrains them from revealing their full potential. There is a great need for automatic BS representations, which will replace the old hand-crafted, variable-length ones. To tackle those problems, we introduce a novel use of Autoencoders (AEs). Our goal is to obtain a low-dimensional, fixed-length, and compact, yet robust repre… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
2
1

Relationship

1
2

Authors

Journals

citations
Cited by 3 publications
(3 citation statements)
references
References 22 publications
0
3
0
Order By: Relevance
“…Similar are the findings when comparing with [8], where the sumBS was used with different RL algorithms on the same domains and environments. A comparison is also possible with [14], where the max accuracy for 45% SER on the CR domain is 52.9% compared to 93.6% in this work, and with [19], which shows that VDAE-LSPI is on average more than 5% better compared to GP-SARSA based approaches.…”
Section: Methodsmentioning
confidence: 58%
See 2 more Smart Citations
“…Similar are the findings when comparing with [8], where the sumBS was used with different RL algorithms on the same domains and environments. A comparison is also possible with [14], where the max accuracy for 45% SER on the CR domain is 52.9% compared to 93.6% in this work, and with [19], which shows that VDAE-LSPI is on average more than 5% better compared to GP-SARSA based approaches.…”
Section: Methodsmentioning
confidence: 58%
“…A second contribution is that our approach capitilizes on a new state-space representation based on noise-robust and compact encodings obtained through unsupervised training of deep Variational Denoising Auto-Encoders (VDAE). In contrast to our recent work in [19], here we combine these encodings with LSPI instead of GP-SARSA. Our scheme proves its efficiency under a variety of noisy conditions, both matched and mismatched, outperforming the current state-ofthe-art.…”
Section: A Contributionmentioning
confidence: 99%
See 1 more Smart Citation