Papers › MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking

MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking

12 Apr 2024arXiv:2404.08559archive 2025-07-28

Tianwen Tang, Tong Zhu, Haodong Liu, Yin Bai, Jia Cheng, Wenliang Chen

Zero-shot dialogue state tracking (DST) transfers knowledge to unseen domains, reducing the cost of annotating new datasets. Previous zero-shot DST models mainly suffer from domain transferring and partial prediction problems. To address these challenges, we propose Mixture of Prefix Experts (MoPE) to establish connections between similar slots in different domains, which strengthens the model transfer performance in unseen domains. Empirical results demonstrate that MoPE-DST achieves the joint goal accuracy of 57.13% on MultiWOZ2.1 and 55.40% on SGD.

PaperPDFCode

Code

ttw1018/mope-dst officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dialogue State Tracking

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DSTSGD

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections