Three Heads Better than One:Pure Entity,Relation Label and Adversarial Training for Cross-domain Few-shot Relation Extraction  

作　　者：Wenlong Fang Chunping Ouyang Qiang Lin Yue Yuan 

机构地区：[1]School of Computer,University of South China,Hengyang,Hunan,421001,China

出　　处：《Data Intelligence》2023年第3期807-823,共17页数据智能（英文）

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:2020J4525,2022J30495;Scientific Research Fund of Hunan Provincial Education Department,Grant/Award Number:18B279,19A439.

摘　　要：In this paper,we study cross-domain relation extraction.Since new data mapping to feature spaces always differs from the previously seen data due to a domain shif,few-shot relation extraction often perform poorly.To solve the problems caused by cross-domain,we propose a method for combining the pure entity,relation labels and adversarial(PERLA).We first use entities and complete sentences for separate encoding to obtain context-independent entity features.Then,we combine relation labels which are useful for relation extraction to mitigate context noise.We combine adversarial to reduce the noise caused by cross-domain.We conducted experiments on the publicly available cross-domain relation extraction dataset Fewrel 2.o[1]o,and the results show that our approach improves accuracy and has better transferability for better adaptation to cross-domain tasks.

关 键 词：Cross-domain Adversarial Learning Prototypical Networks Pure eatity Relation label META-LEARNING 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]