Journal
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022)
Volume -, Issue -, Pages 693-699Publisher
ASSOC COMPUTATIONAL LINGUISTICS-ACL
Keywords
-
Funding
- Beijing Natural Science Foundation [4222037, L181010]
- National Natural Science Foundation of China [61972035]
- Natural Science Foundation of China (NSFC) [62176002]
- Beijing Academy of Artificial Intelligence (BAAI)
Ask authors/readers for more resources
In this work, a hierarchical inductive transfer framework is proposed to learn and deploy dialogue skills continually and efficiently. By introducing adapter modules and using general knowledge in the base adapter to alleviate knowledge interference between tasks, the framework achieves comparable performance on embedded devices.
Pre-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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available