Abstract
As an important component of task-oriented dialogue systems, dialogue state tracking is designed to track the dialogue state through the conversations between users and systems. Multi-domain dialogue state tracking is a challenging task, in which the correlation among different domains and slots needs to consider. Recently, slot self-attention is proposed to provide a data-driven manner to handle it. However, a full-support slot self-attention may involve redundant information interchange. In this paper, we propose a top-k attention-based slot self-attention for multi-domain dialogue state tracking. In the slot self-attention layers, we force each slot to involve information from the other k prominent slots and mask the rest out. The experimental results on two mainstream multi-domain task-oriented dialogue datasets, MultiWOZ 2.0 and MultiWOZ 2.4, present that our proposed approach is effective to improve the performance of multi-domain dialogue state tracking. We also find that the best result is obtained when each slot interchanges information with only a few slots.- Anthology ID:
- 2022.sigdial-1.24
- Volume:
- Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
- Month:
- September
- Year:
- 2022
- Address:
- Edinburgh, UK
- Editors:
- Oliver Lemon, Dilek Hakkani-Tur, Junyi Jessy Li, Arash Ashrafzadeh, Daniel Hernández Garcia, Malihe Alikhani, David Vandyke, Ondřej Dušek
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 231–236
- Language:
- URL:
- https://aclanthology.org/2022.sigdial-1.24
- DOI:
- 10.18653/v1/2022.sigdial-1.24
- Cite (ACL):
- Longfei Yang, Jiyi Li, Sheng Li, and Takahiro Shinozaki. 2022. Multi-Domain Dialogue State Tracking with Top-K Slot Self Attention. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 231–236, Edinburgh, UK. Association for Computational Linguistics.
- Cite (Informal):
- Multi-Domain Dialogue State Tracking with Top-K Slot Self Attention (Yang et al., SIGDIAL 2022)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/2022.sigdial-1.24.pdf