| 基于BERT的金矿地质实体关系抽取模型研究 |
| |
| 引用本文： | 黄徐胜,朱月琴,付立军,刘雨江,唐珂珂,李金.基于BERT的金矿地质实体关系抽取模型研究[J].地质力学学报,2021,27(3):391-399. |
| |
| 作者姓名： | 黄徐胜 朱月琴 付立军 刘雨江 唐珂珂 李金 |
| |
| 作者单位： | 中国科学院大学, 北京 100049;中国科学院沈阳计算技术研究所, 辽宁 沈阳 110168;自然资源部地质信息工程技术创新中心, 北京 100037;中国地质调查局发展研究中心, 北京 100037;中国科学院大学, 北京 100049;中国科学院沈阳计算技术研究所, 辽宁 沈阳 110168;山东大学大数据技术与认知智能实验室, 山东 济南 250100 |
| |
| 基金项目： | 国家自然科学基金项目（41872253）；国家重点研发计划项目（2018YFC1505501）；中国地质调查局地质调查项目（DD20190318） |
| |
| 摘 要： | 金矿实体关系的智能识别是提高金矿文献分析挖掘和知识提取的重要方法和途径。此次研究针对目前金矿实体关系抽取涉及到的核心问题，如金矿实体关系复杂、人工标注信息少等特点，提出了基于BERT(Bidirectional Encoder Representations from Transformer)的远程监督关系抽取模型。并通过金矿地质数据编码、金矿分类和金矿地质实体过滤等模块的优化改进，提高了金矿地质实体关系抽取的准确率。最后通过对金矿文献数据的实体关系抽取实验，验证了该方法的有效性。
|
| 关 键 词： | 远程监督 关系抽取 BERT 地质实体 |
| 收稿时间： | 2020/11/20 0:00:00 |
| 修稿时间： | 2021/1/10 0:00:00 |
Research on a geological entity relation extraction model for gold mine based on BERT |
| |
| HUANG Xusheng,ZHU Yueqin,FU Lijun,LIU Yujiang,TANG Keke,LI Jin.Research on a geological entity relation extraction model for gold mine based on BERT[J].Journal of Geomechanics,2021,27(3):391-399. |
| |
| Authors: | HUANG Xusheng ZHU Yueqin FU Lijun LIU Yujiang TANG Keke LI Jin |
| |
| Institution: | 1.University of Chinese Academy of Sciences, Beijing 100049, China2.Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, Liaoning, China3.Technology Innovation Center of Geological Information, MNR, Beijing 100037, China4.Development Research Center of China Geological Survey, Beijing 100037, China5.Laboratory of Big Data and Artificial Intelligence Technology, Shandong University, Jinan 250100, Shandong, China |
| |
| Abstract: | Intelligent identification of entity relation is an important method and approach to improve literature mining and analysis, and knowledge extraction of gold mine. This study focuses on the core issues affecting current entity relation extraction of gold mine such as complex entity relation and less manual annotation information, and proposes a BERT (Bidirectional Encoder Representations from Transformer) remotely supervised relation extraction model. The accuracy of relation extraction is increased by optimizing and improving the modules related to geological data coding, geological classification and geological entity filtering. And the effectiveness of the model is verified by the entity relation extraction experiment of 290489 pieces of gold ore documents. |
| |
| Keywords: | remote supervision relation extraction BERT geological entity |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《地质力学学报》浏览原始摘要信息 |
| 点击此处可从《地质力学学报》下载免费的PDF全文 |
|
