Lightweight Dialog State Tracking Methods Based on RoBERTa for Resource Constrained Dialog Systems

Dapeng Li, Shuliang Wang*, Boxiang Zhao, Zhiqiang Ma, Xin Xin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Dialog state tracking is a crucial component of task-oriented dialog systems. Pre-trained language models can effectively perform dialog state tracking for task-oriented dialog systems through model fine-tuning. However, it is difficult to apply most methods based on pre-trained language models to resource-constrained systems. To address this challenge, we first propose a model based on RoBERTa, which can perform dialog state tracking tasks more effectively for task-oriented dialog systems. Additionally, we propose two methods to enable our proposed model to be applied to resource-constrained dialog systems. Experimental results on two public datasets show that our proposed model based on RoBERTa can improve the joint goal accuracy of dialog state tracking, and our proposed methods can effectively implement dialog state tracking with less storage space and computing resources.

Original languageEnglish
Title of host publicationGenetic and Evolutionary Computing - Proceedings of the Fifteenth International Conference on Genetic and Evolutionary Computing Volume I, October 6–8, 2023, Kaohsiung, Taiwan
EditorsJerry Chun-Wei Lin, Chin-Shiuh Shieh, Mong-Fong Horng, Shu-Chuan Chu
PublisherSpringer Science and Business Media Deutschland GmbH
Pages112-121
Number of pages10
ISBN (Print)9789819700677
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023 - Kaohsiung, Taiwan, Province of China
Duration: 6 Oct 20238 Oct 2023

Publication series

NameLecture Notes in Electrical Engineering
Volume1145 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023
Country/TerritoryTaiwan, Province of China
CityKaohsiung
Period6/10/238/10/23

Keywords

  • Dialog state tracking
  • Pretrained language models
  • Resource constrained systems

Fingerprint

Dive into the research topics of 'Lightweight Dialog State Tracking Methods Based on RoBERTa for Resource Constrained Dialog Systems'. Together they form a unique fingerprint.

Cite this