Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
This addresses the problem of slot tagging with limited labeled data for NLP applications, representing an incremental advance in adapting few-shot methods to sequence labeling tasks.
The paper tackles few-shot slot tagging by introducing a collapsed dependency transfer mechanism in CRF and a label-enhanced projection network to handle label dependencies and semantics, achieving a 14.64 F1 score improvement over baselines in one-shot settings.
In this paper, we explore the slot tagging with only a few labeled support sentences (a.k.a. few-shot). Few-shot slot tagging faces a unique challenge compared to the other few-shot classification problems as it calls for modeling the dependencies between labels. But it is hard to apply previously learned label dependencies to an unseen domain, due to the discrepancy of label sets. To tackle this, we introduce a collapsed dependency transfer mechanism into the conditional random field (CRF) to transfer abstract label dependency patterns as transition scores. In the few-shot setting, the emission score of CRF can be calculated as a word's similarity to the representation of each label. To calculate such similarity, we propose a Label-enhanced Task-Adaptive Projection Network (L-TapNet) based on the state-of-the-art few-shot classification model -- TapNet, by leveraging label name semantics in representing labels. Experimental results show that our model significantly outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.