Time Masking: Leveraging Temporal Information in Spoken Dialogue Systems

Rylan Conway, Mathias Lambert


Abstract
In a spoken dialogue system, dialogue state tracker (DST) components track the state of the conversation by updating a distribution of values associated with each of the slots being tracked for the current user turn, using the interactions until then. Much of the previous work has relied on modeling the natural order of the conversation, using distance based offsets as an approximation of time. In this work, we hypothesize that leveraging the wall-clock temporal difference between turns is crucial for finer-grained control of dialogue scenarios. We develop a novel approach that applies a time mask, based on the wall-clock time difference, to the associated slot embeddings and empirically demonstrate that our proposed approach outperforms existing approaches that leverage distance offsets, on both an internal benchmark dataset as well as DSTC2.
Anthology ID:
W19-5907
Volume:
Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
Month:
September
Year:
2019
Address:
Stockholm, Sweden
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
56–61
Language:
URL:
https://aclanthology.org/W19-5907
DOI:
10.18653/v1/W19-5907
Bibkey:
Cite (ACL):
Rylan Conway and Mathias Lambert. 2019. Time Masking: Leveraging Temporal Information in Spoken Dialogue Systems. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 56–61, Stockholm, Sweden. Association for Computational Linguistics.
Cite (Informal):
Time Masking: Leveraging Temporal Information in Spoken Dialogue Systems (Conway & Lambert, SIGDIAL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/author-url/W19-5907.pdf
Data
SegTrack-v2