Bidirectional matching and aggregation network for few-shot relation extraction

Zhongcheng Wei; Wenjie Guo; Yunping Zhang; Jieying Zhang; Jijun Zhao

doi:10.7717/peerj-cs.1272

Bidirectional matching and aggregation network for few-shot relation extraction

PeerJ Comput Sci. 2023 Mar 6:9:e1272. doi: 10.7717/peerj-cs.1272. eCollection 2023.

Authors

Zhongcheng Wei^{1

2}, Wenjie Guo^{1

2}, Yunping Zhang^{1

2}, Jieying Zhang^{1

2}, Jijun Zhao^{1

2}

Affiliations

¹ School of Information and Electrical Engineering, Hebei University of Engineering, Handan, Hebei, China.
² Hebei Key Laboratory of Security & Protection Information Sensing and Processing, Handan, Hebei, China.

Abstract

Few-shot relation extraction is used to solve the problem of long tail distribution of data by matching between query instances and support instances. Existing methods focus only on the single direction process of matching, ignoring the symmetry of the data in the process. To address this issue, we propose the bidirectional matching and aggregation network (BMAN), which is particularly powerful when the training data is symmetrical. This model not only tries to extract relations for query instances, but also seeks relational prototypes about the query instances to validate the feature representation of the support set. Moreover, to avoid overfitting in bidirectional matching, the data enhancement method was designed to scale up the number of instances while maintaining the scope of the instance relation class. Extensive experiments on FewRel and FewRel2.0 public datasets are conducted and evaluate the effectiveness of BMAN.

Keywords: Few-shot learning; Knowledge graph; Long-tail distribution; Prototypical network; Relation extraction.

Grants and funding

This research was funded by the Science and Technology Research Project of Higher Education Institutions of Hebei Province under Grant (No. QN2020193) and (No. ZD2020171), the Graduate Demonstration Course Construction Project of Hebei Province under Grant (No. KCJSX2022090) and (No. KCJSX2022091), the Handan Science and Technology Research and Development Program under Grant (No. 21422031288), and the Provincial Innovation Funding Project for Graduate Students of Hebei Province under Grant (No. CXZZBS2022024). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.