Few-shot Named Entity Recognition with Joint Token and Sentence Awareness

作     者：Wen Wen Yongbin Liu Qiang Lin Chunping Ouyang 

作者机构：Computer SchoolUniversity of South ChinaChina Hunan provincial base for scientific and technological innovation cooperationHunanChina 

出 版 物：《Data Intelligence》 (数据智能（英文）)

年 卷 期：2023年第5卷第3期

页      面：767-785页

核心收录：

学科分类：08[工学] 081203[工学-计算机应用技术] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The State Key Program of National Natural Science of China,Grant/Award Number:61533018 National Natural Science Foundation of China,Grant/Award Number:61402220 The Philosophy and Social Science Foundation of Hunan Province,Grant/Award Number:16YBA323 Natural Science Foundation of Hunan Province,Grant/Award Number:2020J4525,2022JJ30495 Scientific Research Fund of Hunan Provincial Education Department,Grant/Award Number:18B279,19A439,22A0316. 

主　　题：Few-shot Learning Named Entity Recognition Prototypical Network 

摘      要：Few-shot learning has been proposed and rapidly emerging as a viable means for completing various tasks.Recently,few-shot models have been used for Named Entity Recognition(NER).Prototypical network shows high efficiency on few-shot NER.However,existing prototypical methods only consider the similarity of tokens in query sets and support sets and ignore the semantic similarity among the sentences which contain these entities.We present a novel model,Few-shot Named Entity Recognition with Joint Token and Sentence Awareness(JTSA),to address the issue.The sentence awareness is introduced to probe the semantic similarity among the sentences.The Token awareness is used to explore the similarity of the tokens.To further improve the robustness and results of the model,we adopt the joint learning scheme on the few-shot NER.Experimental results demonstrate that our model outperforms state-of-the-art models on two standard Fewshot NER datasets.