Saved in:
Bibliographic Details
Main Authors: Tang, Tianwen, Zhu, Tong, Liu, Haodong, Bai, Yin, Cheng, Jia, Chen, Wenliang
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.08559
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911837665099776
author Tang, Tianwen
Zhu, Tong
Liu, Haodong
Bai, Yin
Cheng, Jia
Chen, Wenliang
author_facet Tang, Tianwen
Zhu, Tong
Liu, Haodong
Bai, Yin
Cheng, Jia
Chen, Wenliang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_08559
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking
Tang, Tianwen
Zhu, Tong
Liu, Haodong
Bai, Yin
Cheng, Jia
Chen, Wenliang
Computation and Language
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.
title MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking
topic Computation and Language
url https://arxiv.org/abs/2404.08559