Abstract
Neural dialog models have exhibited strong performance, however their end-to-end nature lacks a representation of the explicit structure of dialog. This results in a loss of generalizability, controllability and a data-hungry nature. Conversely, more traditional dialog systems do have strong models of explicit structure. This paper introduces several approaches for explicitly incorporating structure into neural models of dialog. Structured Fusion Networks first learn neural dialog modules corresponding to the structured components of traditional dialog systems and then incorporate these modules in a higher-level generative model. Structured Fusion Networks obtain strong results on the MultiWOZ dataset, both with and without reinforcement learning. Structured Fusion Networks are shown to have several valuable properties, including better domain generalizability, improved performance in reduced data scenarios and robustness to divergence during reinforcement learning.- Anthology ID:
- W19-5921
- Volume:
- Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
- Month:
- September
- Year:
- 2019
- Address:
- Stockholm, Sweden
- Editors:
- Satoshi Nakamura, Milica Gasic, Ingrid Zuckerman, Gabriel Skantze, Mikio Nakano, Alexandros Papangelis, Stefan Ultes, Koichiro Yoshino
- Venue:
- SIGDIAL
- SIG:
- SIGDIAL
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 165–177
- Language:
- URL:
- https://aclanthology.org/W19-5921
- DOI:
- 10.18653/v1/W19-5921
- Cite (ACL):
- Shikib Mehri, Tejas Srinivasan, and Maxine Eskenazi. 2019. Structured Fusion Networks for Dialog. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 165–177, Stockholm, Sweden. Association for Computational Linguistics.
- Cite (Informal):
- Structured Fusion Networks for Dialog (Mehri et al., SIGDIAL 2019)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/W19-5921.pdf
- Data
- MultiWOZ