TitleHierarchical Inductive Transfer for Continual Dialogue Learning
AuthorsFeng, Shaoxiong
Ren, Xuancheng
Li, Kan
Sun, Xu
AffiliationBeijing Inst Technol, Beijing, Peoples R China
Univ Technol Sydney, Sydney, NSW, Australia
Peking Univ, Sch CS, MOE Key Lab Computat Linguist, Beijing, Peoples R China
Beijing Acad Artificial Intelligence, Beijing, Peoples R China
Issue Date2022
PublisherFINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022)
AbstractPre-trained models have achieved excellent performance on the dialogue task. However, for the continual increase of online chit-chat scenarios, directly fine-tuning these models for each of the new tasks not only explodes the capacity of the dialogue system on the embedded devices but also causes knowledge forgetting on pre-trained models and knowledge interference among diverse dialogue tasks. In this work, we propose a hierarchical inductive transfer framework to learn and deploy the dialogue skills continually and efficiently. First, we introduce the adapter module into pre-trained models for learning new dialogue tasks. As the only trainable module, it is beneficial for the dialogue system on the embedded devices to acquire new dialogue skills with negligible additional parameters. Then, for alleviating knowledge interference between tasks yet benefiting the regularization between them, we further design hierarchical inductive transfer that enables new tasks to use general knowledge in the base adapter without being misled by diverse knowledge in task-specific adapters. Empirical evaluation and analysis indicate that our framework obtains comparable performance under deployment-friendly model capacity.
URIhttp://hdl.handle.net/20.500.11897/654038
ISBN978-1-955917-25-4
IndexedCPCI-SSH(ISSHP)
CPCI-S(ISTP)
Appears in Collections:计算语言学教育部重点实验室

Files in This Work
There are no files associated with this item.

Web of Science®



Checked on Last Week

百度学术™



Checked on Current Time




License: See PKU IR operational policies.