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.
@article{arxiv.2205.01878,
title = {Exploring Entity Interactions for Few-Shot Relation Learning (Student Abstract)},
author = {YI Liang and Shuai Zhao and Bo Cheng and Yuwei Yin and Hao Yang},
journal= {arXiv preprint arXiv:2205.01878},
year = {2022}
}
Comments
Accepted as a Finalist Paper of Student Abstract Session of AAAI 2022