Exploring Entity Interactions for Few-Shot Relation Learning (Student Abstract)

TL;DR

This paper introduces TransAM, a transformer-based model that captures intra- and inter-triple entity interactions for improved few-shot relation learning, demonstrating effectiveness on benchmark datasets.

Contribution

The paper proposes a novel transformer-based approach, TransAM, that models entity interactions within and between triples for few-shot relation learning.

Findings

TransAM outperforms existing methods on NELL-One and Wiki-One datasets.

Entity interaction modeling improves relation learning accuracy.

Transformer architecture effectively captures semantic entity relations.

Abstract

Few-shot relation learning refers to infer facts for relations with a limited number of observed triples. Existing metric-learning methods for this problem mostly neglect entity interactions within and between triples. In this paper, we explore this kind of fine-grained semantic meanings and propose our model TransAM. Specifically, we serialize reference entities and query entities into sequence and apply transformer structure with local-global attention to capture both intra- and inter-triple entity interactions. Experiments on two public benchmark datasets NELL-One and Wiki-One with 1-shot setting prove the effectiveness of TransAM.