Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning

Abstract

Standard few-shot relation classification (RC) is designed to learn a robust classifier with only few labeled data for each class. However, previous works rarely investigate the effects of a different number of classes (i.e., $N$-way) and number of labeled data per class (i.e., $K$-shot) during training vs. testing. In this work, we define a new task, \textit{inconsistent few-shot RC}, where the model needs to handle the inconsistency of $N$ and $K$ between training and testing. To address this new task, we propose Prototype Network-based cross-attention contrastive learning (ProtoCACL) to capture the rich mutual interactions between the support set and query set. Experimental results demonstrate that our ProtoCACL can outperform the state-of-the-art baseline model under both inconsistent $K$ and inconsistent $N$ settings, owing to its more robust and discriminate representations. Moreover, we identify that in the inconsistent few-shot learning setting, models can achieve better performance with \textit{less data} than the standard few-shot setting with carefully-selected $N$ and $K$. In the end of the paper, we provide further analyses and suggestions to systematically guide the selection of $N$ and $K$ under different scenarios.

References in corpus (7)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• On First-Order Meta-Learning Algorithms
• Simple BERT Models for Relation Extraction and Semantic Role Labeling
• Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems
• A Theoretical Analysis of the Number of Shots in Few-Shot Learning
• MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging