|
|||||
|
|
| 基于远程监督的关系抽取研究综述 | |
| 引用本文： | 白龙,靳小龙,席鹏弼,程学旗.基于远程监督的关系抽取研究综述[J].中文信息学报,2019,33(10):10-17. |
| 作者姓名： | 白龙 靳小龙 席鹏弼 程学旗 |
| 作者单位： | 1.中国科学院 计算技术研究所 中国科学院网络数据科学与技术重点实验室,北京 100190; 2.中国科学院大学 计算机与控制学院,北京 100190 |
| 基金项目： | 国家重点研发计划(2016YFB1000902);国家自然科学基金(61772501,61572473,61572469,91646120) |
| 摘 要： | 关系抽取作为信息抽取的一项关键技术,在知识库自动构建、问答系统等领域有着极为重要的意义,一直以来受到人们的关注。远程监督关系抽取技术通过外部知识库作为监督源,自动对语料库进行标注,能够大量节省人工标注成本,因而受到了研究者们的重视。该文针对远程监督关系抽取技术做了较为系统性的梳理,将已有方法分为基于概率图的、基于矩阵补全的和基于嵌入的三大类,并且对其当前面临的挑战进行了探讨,最后总结并展望了远程监督关系抽取技术未来的发展。 |
| 关 键 词： | 远程监督 关系抽取 信息抽取 |
A Survey on Distant Supervision Based Relation Extraction |
|
| BAI Long,JIN Xiaolong,XI Pengbi,CHENG Xueqi.A Survey on Distant Supervision Based Relation Extraction[J].Journal of Chinese Information Processing,2019,33(10):10-17. | |
| Authors: | BAI Long JIN Xiaolong XI Pengbi CHENG Xueqi |
| Affiliation: | 1.CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China; 2.School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100190, China |
| Abstract: | As a key technique of information extraction, relation extraction is of great importance to many tasks such as automatic knowledge base construction and question answering systems. Distant supervision for relation extraction uses an external knowledge base as supervision signals to automatically label corpus, which can reduce the high cost of manual labelling. This paper presents a systematic survey to distantly supervised relation extraction. It classifies the existing methods into three types, including probabilistic graph-based, matrix completion-based and embedding-based ones. This paper also discusses the challenges and the future research directions of distantly supervised relation extraction. |
| Keywords: | distant supervision relation extraction information extraction |
| 点击此处可从《中文信息学报》浏览原始摘要信息 | |
| 点击此处可从《中文信息学报》下载全文 | |