A Contrastive learning-based Task Adaptation model for few-shot intent recognition
作者:
Highlights:
• We employ a CTA model to get the task-unique feature for few-shot intent recognition.
• We introduce a contrastive-based loss function to well separate different classes.
• We use the semantics of label name as an anchor feature of each class to fix bias.
• Our model performs particularly well in multi-domain and cross-domain scenarios.
摘要
•We employ a CTA model to get the task-unique feature for few-shot intent recognition.•We introduce a contrastive-based loss function to well separate different classes.•We use the semantics of label name as an anchor feature of each class to fix bias.•Our model performs particularly well in multi-domain and cross-domain scenarios.
论文关键词:Intent recognition,Few-shot learning,Contrastive learning
论文评审过程:Received 6 October 2021, Revised 21 December 2021, Accepted 30 December 2021, Available online 7 February 2022, Version of Record 7 February 2022.
论文官网地址:https://doi.org/10.1016/j.ipm.2021.102863