Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network

Abstract

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.

Accepted by ACL2020

References in corpus (6)

• Prototypical Networks for Few-shot Learning
• Matching Networks for One Shot Learning
• Few-Shot Generalization Across Dialogue Tasks
• Adapting Meta Knowledge Graph Information for Multi-Hop Reasoning over Few-Shot Relations
• Neural Snowball for Few-Shot Relation Learning
• Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning

Cited by in corpus (2)

• Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
• Linguistically-Enriched and Context-Aware Zero-shot Slot Filling