Context-Aware Module Selection in Modular Dialog Systems

Jan Nehring, René Marcel Berk, Stefan Hillmann


Abstract
In modular dialog systems, a dialog system consists of multiple conversational agents. The task “module selection” selects the appropriate sub-dialog system for an incoming user utterance. Current models for module selection use features derived from the current user turn only, such as the utterances text or confidence values of the natural language understanding systems of the individual conversational agents, or they perform text classification on the user utterance. However, dialogs often span multiple turns, and turns are embedded into a context. Therefore, looking at the current user turn only is a source of error in certain situations. This work proposes four models for module selection that include the dialog history and the current user turn into module selection. We show that these models surpass the current state of the art in module selection.
Anthology ID:
2023.ranlp-1.85
Volume:
Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing
Month:
September
Year:
2023
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd., Shoumen, Bulgaria
Note:
Pages:
785–791
Language:
URL:
https://aclanthology.org/2023.ranlp-1.85
DOI:
Bibkey:
Cite (ACL):
Jan Nehring, René Marcel Berk, and Stefan Hillmann. 2023. Context-Aware Module Selection in Modular Dialog Systems. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, pages 785–791, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.
Cite (Informal):
Context-Aware Module Selection in Modular Dialog Systems (Nehring et al., RANLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.ranlp-1.85.pdf