Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs

TL;DR

This paper introduces a Bayesian meta-learning method utilizing a global relation graph and stochastic gradient Langevin dynamics to improve few-shot relation extraction, demonstrating superior performance on benchmark datasets.

Contribution

It proposes a novel Bayesian meta-learning framework with a relation graph and Langevin dynamics for few-shot relation extraction, enhancing generalization to new relations.

Findings

Outperforms baseline methods in few-shot and zero-shot settings

Effectively models relation uncertainties with Bayesian approach

Leverages relation graph for better prototype initialization

Abstract

This paper studies few-shot relation extraction, which aims at predicting the relation for a pair of entities in a sentence by training with a few labeled examples in each relation. To more effectively generalize to new relations, in this paper we study the relationships between different relations and propose to leverage a global relation graph. We propose a novel Bayesian meta-learning approach to effectively learn the posterior distribution of the prototype vectors of relations, where the initial prior of the prototype vectors is parameterized with a graph neural network on the global relation graph. Moreover, to effectively optimize the posterior distribution of the prototype vectors, we propose to use the stochastic gradient Langevin dynamics, which is related to the MAML algorithm but is able to handle the uncertainty of the prototype vectors. The whole framework can be effectively and efficiently optimized in an end-to-end fashion. Experiments on two benchmark datasets prove the effectiveness of our proposed approach against competitive baselines in both the few-shot and zero-shot settings.