Addressing Slot-Value Changes in Task-oriented Dialogue Systems through Dialogue Domain Adaptation

Tiziano Labruna, Bernardo Magnini


Abstract
Recent task-oriented dialogue systems learn a model from annotated dialogues, and such dialogues are in turn collected and annotated so that they are consistent with certain domain knowledge. However, in real scenarios, domain knowledge is subject to frequent changes, and initial training dialogues may soon become obsolete, resulting in a significant decrease in the model performance. In this paper, we investigate the relationship between training dialogues and domain knowledge, and propose Dialogue Domain Adaptation, a methodology aiming at adapting initial training dialogues to changes intervened in the domain knowledge. We focus on slot-value changes (e.g., when new slot values are available to describe domain entities) and define an experimental setting for dialogue domain adaptation. First, we show that current state-of-the-art models for dialogue state tracking are still poorly robust to slot-value changes of the domain knowledge. Then, we compare different domain adaptation strategies, showing that simple techniques are effective to reduce the gap between training dialogues and domain knowledge.
Anthology ID:
2021.ranlp-1.89
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
780–789
Language:
URL:
https://aclanthology.org/2021.ranlp-1.89
DOI:
Bibkey:
Cite (ACL):
Tiziano Labruna and Bernardo Magnini. 2021. Addressing Slot-Value Changes in Task-oriented Dialogue Systems through Dialogue Domain Adaptation. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 780–789, Held Online. INCOMA Ltd..
Cite (Informal):
Addressing Slot-Value Changes in Task-oriented Dialogue Systems through Dialogue Domain Adaptation (Labruna & Magnini, RANLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ranlp-1.89.pdf
Data
MultiWOZ