Granularity-Aware Area Prototypical Network With Bimargin Loss for Few Shot Relation Classification

• Published in: IEEE transactions on knowledge and data engineering Vol. 35; no. 5; pp. 4852 - 4866
• Main Authors: Ren, Haopeng, Cai, Yi, Lau, Raymond Y.K., Leung, Ho-fung, Li, Qing
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.05.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Classification; Computational modeling; Data mining; Data models; Dispersion; few-shot learning; metric learning; Networks; Optimization; Performance evaluation; Prototypes; prototypical network; Relation classification; Robustness; Semantics; Task analysis; Training
• ISSN: 1041-4347; 1558-2191
• DOI: 10.1109/TKDE.2022.3147455

Relation Classification is one of the most important tasks in text mining. Previous methods either require large-scale manually-annotated data or rely on distant supervision approaches which suffer from the long-tail problem. To reduce the expensive manually-annotating cost and solve the long-tail problem, prototypical networks are widely used in few-shot RC tasks. Despite their remarkable performance, current prototypical networks ignore the different granularities of relations, which degrades the classification performance dramatically. Moreover, the optimization of current prototypical networks simply relies on the cross-entropy loss, which cannot consider the intra-relation compactness and the dispersion among relations in a semantic space. It is not robust enough for the current prototypical network in real-world and complicated scenarios. In this paper, we propose an area prototypical network with a granularity-aware measurement, aiming to consider the different granularities of relations. Each relation is represented as an area whose width can reflect the granularity level of relation. Moreover, to improve the robustness, bimargin loss is designed to force area prototypical network to improve the intra-relation compactness and inter-relation dispersion for the feature representation in a semantic space. Extensive experiments on two public datasets are conducted and evaluate the effectiveness of our proposed model.