Geological Time Information Extraction from Chinese Text Based on BiLSTM-CRF

doi:10.11867/j.issn.1001-8166.2021.017

Advances in Earth Science ›› 2021, Vol. 36 ›› Issue (2): 211-220. doi: 10.11867/j.issn.1001-8166.2021.017

Geological Time Information Extraction from Chinese Text Based on BiLSTM-CRF

Wencong LIU ¹( ), Chunju ZHANG ¹ ^, ³( ), Chen WANG ¹, Xueying ZHANG ², Yueqin ZHU ⁴, Shoutao JIAO ⁴, Yanxu LU ²

^1.School of Civil Engineering，Hefei University of Technology，Hefei 230009，China
^2.MOE Key Laboratory of Virtual Geographical Environment，Nanjing Normal University，Nanjing 210023，China
^3.Key Laboratory of Urban Land Resources Monitoring and Simulation，Shenzhen Guangdong 518034，China
^4.Development Research Center，China Geological Survey，Beijing 100037，China

Received:2020-11-04 Revised:2021-01-15 Online:2021-04-13 Published:2021-04-19
Contact: Chunju ZHANG E-mail:2019110618@mail.hfut.edu.cn;zcjtwz@sina.com
About author:LIU Wencong （1998-）， female， Hefei City， Anhui Province， Associate professor. Research areas include cartography and geographical information engineering. E-mail： 2019110618@mail.hfut.edu.cn
Supported by:
the Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources "The spatial semantic computing for qualitative location of land resources information perception"(KF-2020-05-084);The National Natural Science Foundation of China "Geographical knowledge graph construction method combining text and map"(41971337)

(RichHTML) ( 14) PDF ( 498 ) Cited

Wencong LIU, Chunju ZHANG, Chen WANG, Xueying ZHANG, Yueqin ZHU, Shoutao JIAO, Yanxu LU. Geological Time Information Extraction from Chinese Text Based on BiLSTM-CRF[J]. Advances in Earth Science, 2021, 36(2): 211-220.

Time information runs through the entire process of the creation， development and extinction of geological entities， reflecting the state and evolution of geological entities. In particular， the expression of geological time is usually related to metallogenetic mechanism and space time evolution regularity. This paper designs and implements a universal time and geological time information extraction method based on deep learning methods. Combining the description characteristics of time information in the Chinese text of geological and mineral resources， the time information in geological reports and documentation is divided into two types： universal time information and geological time information， and the two types of time information are subdivided. The self-developed geological time information corpus is constructed using cross-validation and opinion feedback mode. The time information extraction method based on BiLSTM-CRF is realized， and this method is compared with CNN and CRF. The experimental results show that the BiLSTM-CRF model is better than the mainstream model in time information extraction， and the F1-Measure of the overall time extraction reaches 95.49%， which solves the problem of standardized expression and structured extraction of time information in geological text.

No related articles found!

Viewed

Full text

Abstract