COLINGAug, 2022
基于实体级原型网络和分散分布式原型 模型增强的小样本命名实体识别
Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes
Bin Ji, Shasha Li, Shaoduo Gan, Jie Yu, Jun Ma...
TL;DREP-Net is proposed to improve labeled dependency and prototype distribution in few-shot named entity recognition, achieving better performance than previous models.