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

05/04/2022

∙

by   Yi Liang, et al.

∙

Beijing University of Posts and Telecommunications

∙

HUAWEI Technologies Co., Ltd.

∙

2

∙

share

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.