A case study on the importance of belief state representation for dialogue policy management
File(s)
Submitted version
Author(s)
Kotti, M
Diakoloukas, Vassilios
Papangelis, Alexandros
Lagoudakis, Michaill
Stylianou, Yannis
Type
Conference Paper
Abstract
A key component of task-oriented dialogue systems is the belief
state representation, since it directly affects the policy learning
efficiency. In this paper, we propose a novel, binary, compact,
yet scalable belief state representation. We compare the stan-
dard verbose belief state representation (268 dimensions) with
the domain-independent representation (57 dimensions) and the
proposed representation (13 or 4 dimensions). To test those
representations, the recently introduced Advantage Actor Critic
(A2C) algorithm is exploited. The latter has not been tested
before for any representation apart from the verbose one. We
study the effect of the belief state representation within A2C un-
der 0%, 15%, 30%, and 45% semantic error rate and conclude
that the novel binary representation in general outperforms both
the domain-independent and the verbose belief state represen-
tation. Further, the robustness of the binary representation is
tested under more realistic scenarios with mismatched semantic
error rates, within the A2C and DQN algorithms. The results
indicate that the proposed compact, binary representation per-
forms better or similarly to the other representations, being an
efficient and promising alternative to the full belief.
state representation, since it directly affects the policy learning
efficiency. In this paper, we propose a novel, binary, compact,
yet scalable belief state representation. We compare the stan-
dard verbose belief state representation (268 dimensions) with
the domain-independent representation (57 dimensions) and the
proposed representation (13 or 4 dimensions). To test those
representations, the recently introduced Advantage Actor Critic
(A2C) algorithm is exploited. The latter has not been tested
before for any representation apart from the verbose one. We
study the effect of the belief state representation within A2C un-
der 0%, 15%, 30%, and 45% semantic error rate and conclude
that the novel binary representation in general outperforms both
the domain-independent and the verbose belief state represen-
tation. Further, the robustness of the binary representation is
tested under more realistic scenarios with mismatched semantic
error rates, within the A2C and DQN algorithms. The results
indicate that the proposed compact, binary representation per-
forms better or similarly to the other representations, being an
efficient and promising alternative to the full belief.
Date Acceptance
2018-06-03
Citation
Interspeech 2018, pp.986-990
Publisher
ISCA
Start Page
986
End Page
990
Journal / Book Title
Interspeech 2018
Copyright Statement
©2018 ISCA
Source
INTERSPEECH 2018
Subjects
Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
Computer Science
Engineering
dialogue systems
belief state
binary belief state representation
domain-independent parametrisation
Publication Status
Published
Start Date
2018-09-02
Finish Date
2018-09-06
Coverage Spatial
Hyderabad, India