MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction

TL;DR

MapRE introduces a semantic mapping framework that combines label-aware and label-agnostic information, significantly enhancing low-resource relation extraction performance by leveraging both types of semantic knowledge during pretraining and fine-tuning.

Contribution

The paper proposes a novel framework that integrates label-aware and label-agnostic semantic mappings for low-resource relation extraction, addressing a key limitation of previous models.

Findings

Significant performance improvement on low-resource datasets

Effective combination of label-aware and label-agnostic information

Enhanced generalization in relation extraction tasks

Abstract

Neural relation extraction models have shown promising results in recent years; however, the model performance drops dramatically given only a few training samples. Recent works try leveraging the advance in few-shot learning to solve the low resource problem, where they train label-agnostic models to directly compare the semantic similarities among context sentences in the embedding space. However, the label-aware information, i.e., the relation label that contains the semantic knowledge of the relation itself, is often neglected for prediction. In this work, we propose a framework considering both label-agnostic and label-aware semantic mapping information for low resource relation extraction. We show that incorporating the above two types of mapping information in both pretraining and fine-tuning can significantly improve the model performance on low-resource relation extraction tasks.