Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling
Jie Han, Yixiong Zou, Haozhao Wang, Jun Wang, Wei Liu, Yao Wu, Tao Zhang, Ruixuan Li
Abstract
Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.
BibTeX
@article{Han_Zou_Wang_Wang_Liu_Wu_Zhang_Li_2024, title={Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/29775}, DOI={10.1609/aaai.v38i16.29775}, abstractNote={Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer the model to target domains where only rarely labeled data is available. However, experience transferring as a whole usually suffers from gaps that exist among source domains and target domains. For instance, transferring domain-specific-knowledge-related experience is difficult. To tackle this problem, we propose a new method that explicitly decouples the transferring of general-semantic-representation-related experience and the domain-specific-knowledge-related experience. Specifically, for domain-specific-knowledge-related experience, we design two modules to capture intent-slot relation and slot-slot relation respectively. Extensive experiments on Snips and FewJoint datasets show that our method achieves state-of-the-art performance. The method improves the joint accuracy metric from 27.72% to 42.20% in the 1-shot setting, and from 46.54% to 60.79% in the 5-shot setting.}, number={16}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Han, Jie and Zou, Yixiong and Wang, Haozhao and Wang, Jun and Liu, Wei and Wu, Yao and Zhang, Tao and Li, Ruixuan}, year={2024}, month={Mar.}, pages={18171-18179} }