Knowledge-enhanced prototypical network with class cluster loss for few-shot relation classification

• Published in: PloS one Vol. 18; no. 6; p. e0286915
• Main Authors: Liu, Tao, Ke, Zunwang, Li, Yanbing, Silamu, Wushour
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 08.06.2023; Public Library of Science (PLoS)
• Subjects: Biology and Life Sciences; Classification; Clusters; Computational linguistics; Computer and Information Sciences; Data mining; Data visualization; Datasets; Design; Engineering and Technology; Evaluation; Graph neural networks; Labeling; Language processing; Metric space; Modelling; Natural language; Natural language interfaces; Natural language processing; Neural networks; Optimization algorithms; Outliers (statistics); Physical Sciences; Prototypes; Representations; Semantics; Similarity; Social Sciences; Training; China; Bulgaria

Few-shot Relation Classification identifies the relation between target entity pairs in unstructured natural language texts by training on a small number of labeled samples. Recent prototype network-based studies have focused on enhancing the prototype representation capability of models by incorpor...