TY - GEN
T1 - Lightweight Dialog State Tracking Methods Based on RoBERTa for Resource Constrained Dialog Systems
AU - Li, Dapeng
AU - Wang, Shuliang
AU - Zhao, Boxiang
AU - Ma, Zhiqiang
AU - Xin, Xin
N1 - Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2024
Y1 - 2024
N2 - 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.
AB - 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.
KW - Dialog state tracking
KW - Pretrained language models
KW - Resource constrained systems
UR - http://www.scopus.com/inward/record.url?scp=85186710932&partnerID=8YFLogxK
U2 - 10.1007/978-981-97-0068-4_11
DO - 10.1007/978-981-97-0068-4_11
M3 - Conference contribution
AN - SCOPUS:85186710932
SN - 9789819700677
T3 - Lecture Notes in Electrical Engineering
SP - 112
EP - 121
BT - Genetic and Evolutionary Computing - Proceedings of the Fifteenth International Conference on Genetic and Evolutionary Computing Volume I, October 6–8, 2023, Kaohsiung, Taiwan
A2 - Lin, Jerry Chun-Wei
A2 - Shieh, Chin-Shiuh
A2 - Horng, Mong-Fong
A2 - Chu, Shu-Chuan
PB - Springer Science and Business Media Deutschland GmbH
T2 - 15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023
Y2 - 6 October 2023 through 8 October 2023
ER -