Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking
Yue Feng, Aldo Lipani, Fanghua Ye, Qiang Zhang, Emine Yilmaz

TL;DR
This paper introduces DSGFNet, a novel dynamic schema graph fusion network for multi-domain dialogue state tracking that explicitly models relations and generalizes to unseen domains, improving performance on benchmark datasets.
Contribution
The paper proposes DSGFNet, which dynamically fuses prior and dialogue-aware relations in schema graphs to enhance multi-domain dialogue state tracking and domain generalization.
Findings
Outperforms existing methods on SGD, MultiWOZ2.1, and MultiWOZ2.2 datasets.
Effectively models relations among domains and slots.
Facilitates knowledge transfer to unseen domains.
Abstract
Dialogue State Tracking (DST) aims to keep track of users' intentions during the course of a conversation. In DST, modelling the relations among domains and slots is still an under-studied problem. Existing approaches that have considered such relations generally fall short in: (1) fusing prior slot-domain membership relations and dialogue-aware dynamic slot relations explicitly, and (2) generalizing to unseen domains. To address these issues, we propose a novel \textbf{D}ynamic \textbf{S}chema \textbf{G}raph \textbf{F}usion \textbf{Net}work (\textbf{DSGFNet}), which generates a dynamic schema graph to explicitly fuse the prior slot-domain membership relations and dialogue-aware dynamic slot relations. It also uses the schemata to facilitate knowledge transfer to new domains. DSGFNet consists of a dialogue utterance encoder, a schema graph encoder, a dialogue-aware schema graph evolving…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Speech and dialogue systems · Cognitive Functions and Memory
MethodsDynamic Sparse Training · Stochastic Gradient Descent
