Scaling Multi-Domain Dialogue State Tracking via Query Reformulation
Pushpendre Rastogi, Arpit Gupta, Tongfei Chen, Mathias Lambert
Abstract
We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the entities relevant to the conversation across turns. Tracking conversational state is particularly challenging in a multi-domain scenario when there exist multiple spoken language understanding (SLU) sub-systems, and each SLU sub-system operates on its domain-specific meaning representation. While previous approaches have addressed the disparate schema issue by learning candidate transformations of the meaning representation, in this paper, we instead model the reference resolution as a dialogue context-aware user query reformulation task – the dialog state is serialized to a sequence of natural language tokens representing the conversation. We develop our model for query reformulation using a pointer-generator network and a novel multi-task learning setup. In our experiments, we show a significant improvement in absolute F1 on an internal as well as a, soon to be released, public benchmark respectively.- Anthology ID:
- N19-2013
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Anastassia Loukina, Michelle Morales, Rohit Kumar
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 97–105
- Language:
- URL:
- https://aclanthology.org/N19-2013
- DOI:
- 10.18653/v1/N19-2013
- Cite (ACL):
- Pushpendre Rastogi, Arpit Gupta, Tongfei Chen, and Mathias Lambert. 2019. Scaling Multi-Domain Dialogue State Tracking via Query Reformulation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Industry Papers), pages 97–105, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Scaling Multi-Domain Dialogue State Tracking via Query Reformulation (Rastogi et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/N19-2013.pdf
- Data
- CQR