Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling
This addresses the challenge of transferring models to new domains with limited labeled data in natural language processing, representing an incremental advance over existing methods.
The paper tackles the problem of few-shot intent classification and slot filling by decoupling the transfer of general semantic representation and domain-specific knowledge, achieving state-of-the-art performance with joint accuracy improvements from 27.72% to 42.20% in 1-shot and from 46.54% to 60.79% in 5-shot settings.
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.