| 引用本文: | 鄂海红,张文静,肖思琪,程瑞,胡莺夕,周筱松,牛佩晴.深度学习实体关系抽取研究综述.软件学报,2019,30(6):1793-1818 |
| |
|
| 本文已被：浏览 8291次 下载 7420次 |
码上扫一扫！ |
|
|
| 深度学习实体关系抽取研究综述 |
|
鄂海红1,2, 张文静1,2, 肖思琪1,2, 程瑞1,2, 胡莺夕1,2, 周筱松1,2, 牛佩晴1,2
|
|
1.北京邮电大学 计算机学院 数据科学与服务中心, 北京 100876;2.教育部信息网络工程研究中心(北京邮电大学), 北京 100876
|
|
| 摘要: |
| 实体关系抽取作为信息抽取、自然语言理解、信息检索等领域的核心任务和重要环节，能够从文本中抽取实体对间的语义关系.近年来，深度学习在联合学习、远程监督等方面上的应用，使关系抽取任务取得了较为丰富的研究成果.目前，基于深度学习的实体关系抽取技术，在特征提取的深度和模型的精确度上已经逐渐超过了传统基于特征和核函数的方法.围绕有监督和远程监督两个领域，系统总结了近几年来中外学者基于深度学习的实体关系抽取研究进展，并对未来可能的研究方向进行了探讨和展望. |
| 关键词: 实体关系抽取 深度学习 联合学习 远程监督 生成对抗网络 |
| DOI：10.13328/j.cnki.jos.005817 |
| 分类号: |
| 基金项目:国家重点研发计划（2018YFB1403501） |
|
| Survey of Entity Relationship Extraction Based on Deep Learning |
|
E Hai-Hong1,2, ZHANG Wen-Jing1,2, XIAO Si-Qi1,2, CHENG Rui1,2, HU Ying-Xi1,2, ZHOU Xiao-Song1,2, NIU Pei-Qing1,2
|
|
1.Data Science and Service Center, School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China;2.Engineering Research Center of Information Networks of Ministry of Education (Beijing University of Posts and Telecommunications), Beijing 100876, China
|
| Abstract: |
| Entity relation extraction is a core task and an important part in the fields of information extraction, natural language understanding, and information retrieval. It can extract the semantic relationships between entity pairs from the texts. In recent years, the application of deep learning in the fields of joint learning, remote supervision has resulted in relatively abundant research results in relation extraction tasks. At present, entity relationship extraction technology based on deep learning has gradually exceeded the traditional methods which are based on features and kernel functions in terms of the depth of feature extraction and the accuracy. This paper focuses on the two fields of supervision and remote supervision. It systematically summarizes the research progress of Chinese and overseas scholars' deep relationship-based entity relationship extraction in recent years, and discusses and prospects future possible research directions as well. |
| Key words: entity relationship extraction deep learning joint learning remote supervision generative adversarial network |
