典型文献
Adversarial Training for Supervised Relation Extraction
文献摘要：
Most supervised methods for relation extraction(RE)involve time-consuming human annotation.Distant supervision for RE is an efficient method to obtain large corpora that contains thousands of instances and various relations.However,the existing approaches rely heavily on knowledge bases(e.g.,Freebase),thereby introducing data noise.Various relations and noisy labeling instances make the issue difficult to solve.In this study,we propose a model based on a piecewise convolution neural network with adversarial training.Inspired by generative adversarial networks,we adopt a heuristic algorithm to identify noisy datasets and apply adversarial training to RE.Experiments on the extended dataset of SemEval-2010 Task 8 show that our model can obtain more accurate training data for RE and significantly outperforms several competitive baseline models.Our model has an F1 score of 89.61％.
文献关键词：
中图分类号：
作者姓名：
Yanhua Yu;Kanghao He;Jie Li
作者机构：
School of Computer Science(National Pilot Software Engineering School),Beijing University of Posts and Telecommunications,Beijing 100876,China
文献出处：
引用格式：
[1]Yanhua Yu;Kanghao He;Jie Li-.Adversarial Training for Supervised Relation Extraction)[J].清华大学学报自然科学版（英文版）,2022(03):610-618
A类：
B类：
Adversarial,Training,Supervised,Relation,Extraction,Most,supervised,methods,extraction,RE,involve,consuming,human,annotation,Distant,supervision,efficient,obtain,large,corpora,that,contains,thousands,instances,various,relations,However,existing,approaches,rely,heavily,knowledge,bases,Freebase,thereby,introducing,noise,Various,noisy,labeling,make,issue,difficult,solve,this,study,propose,piecewise,convolution,neural,adversarial,training,Inspired,generative,networks,adopt,heuristic,algorithm,identify,datasets,apply,Experiments,extended,SemEval,Task,show,our,more,accurate,significantly,outperforms,several,competitive,baseline,models,Our,has,score
AB值：
0.694398
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
