Adversarial Training for Supervised Relation Extraction  

作　　者：Yanhua Yu Kanghao He Jie Li 

机构地区：[1]School of Computer Science(National Pilot Software Engineering School),Beijing University of Posts and Telecommunications,Beijing 100876,China

出　　处：《Tsinghua Science and Technology》2022年第3期610-618,共9页清华大学学报（自然科学版（英文版）

基　　金：supported in part by the National Natural Science Foundation of China (Nos. U1936104 and 2020JCJQ-ZD-012)。

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%.

关 键 词：relation extraction piecewise convolution neural network adversarial training generative adversarial network 

分 类 号：TN911.4[电子电信—通信与信息系统] TP18[电子电信—信息与通信工程]