Joint extraction method for entity relations from mineral resources reports integrating dependency parsing and improved graph convolutional networks
[Display omitted] •Propose a GCN entity relationship joint extraction model based on dependency syntax analysis.•Propose a GCN with stacked pointer networks to address long entity and overlapping entity.•Propose the use of the axial attention mechanism and BiLSTM model to effectively capture context...
Saved in:
Published in | Ore geology reviews Vol. 182; p. 106640 |
---|---|
Main Authors | , , , , , , |
Format | Journal Article |
Language | English |
Published |
Elsevier B.V
01.07.2025
|
Subjects | |
Online Access | Get full text |
ISSN | 0169-1368 1872-7360 |
DOI | 10.1016/j.oregeorev.2025.106640 |
Cover
Abstract | [Display omitted]
•Propose a GCN entity relationship joint extraction model based on dependency syntax analysis.•Propose a GCN with stacked pointer networks to address long entity and overlapping entity.•Propose the use of the axial attention mechanism and BiLSTM model to effectively capture contextual semantic features.
Geological reports, as crucial technical documents reflecting the outcomes of geological survey work, encapsulate extensive expert and domain knowledge. Geological knowledge graphs integrate vast amounts of data, facilitating efficient and rapid extraction of knowledge embedded within geoscientific data. The extraction of geological entity relations is a key method in creating these knowledge graphs. Existing techniques for extracting geological entities and their relations encounter difficulties such entity overlap, relation overlap, and the challenge of obtaining deep semantic information because of the vastness and complexity of geological data. Our study suggests a collaborative extraction model for entity relations that integrates dependency syntactic relations with a graph convolutional network (GCN) in order to address these problems. This model learns dependency syntactic structures and deep semantic information by building a GCN that includes dependency syntactic relations. A pointer network decoder is then added to increase entity relation extraction efficiency. Dependencies between words in a phrase, such as subject-verb and verb-object relations, are revealed via dependency syntactic analysis. By structuring these dependencies into a graph, the model captures syntactic structural information. Through operations involving adjacency matrices and feature matrices, the model effectively propagates and aggregates node information, thereby capturing the global dependency syntactic structure and deep semantic information of sentences. The integration of dependency syntactic relations with GCN processing enables the model to more accurately comprehend entity relations within sentences. Results from experiments show that this model successfully tackles problems like overlapping entity relations and the challenge of gleaning deep semantic information from geological texts. It achieves a 79.73% accuracy rate and a 77.98% F1 score on geological text datasets. |
---|---|
AbstractList | [Display omitted]
•Propose a GCN entity relationship joint extraction model based on dependency syntax analysis.•Propose a GCN with stacked pointer networks to address long entity and overlapping entity.•Propose the use of the axial attention mechanism and BiLSTM model to effectively capture contextual semantic features.
Geological reports, as crucial technical documents reflecting the outcomes of geological survey work, encapsulate extensive expert and domain knowledge. Geological knowledge graphs integrate vast amounts of data, facilitating efficient and rapid extraction of knowledge embedded within geoscientific data. The extraction of geological entity relations is a key method in creating these knowledge graphs. Existing techniques for extracting geological entities and their relations encounter difficulties such entity overlap, relation overlap, and the challenge of obtaining deep semantic information because of the vastness and complexity of geological data. Our study suggests a collaborative extraction model for entity relations that integrates dependency syntactic relations with a graph convolutional network (GCN) in order to address these problems. This model learns dependency syntactic structures and deep semantic information by building a GCN that includes dependency syntactic relations. A pointer network decoder is then added to increase entity relation extraction efficiency. Dependencies between words in a phrase, such as subject-verb and verb-object relations, are revealed via dependency syntactic analysis. By structuring these dependencies into a graph, the model captures syntactic structural information. Through operations involving adjacency matrices and feature matrices, the model effectively propagates and aggregates node information, thereby capturing the global dependency syntactic structure and deep semantic information of sentences. The integration of dependency syntactic relations with GCN processing enables the model to more accurately comprehend entity relations within sentences. Results from experiments show that this model successfully tackles problems like overlapping entity relations and the challenge of gleaning deep semantic information from geological texts. It achieves a 79.73% accuracy rate and a 77.98% F1 score on geological text datasets. |
ArticleNumber | 106640 |
Author | Jin, Xiangguo Wu, Qirui Tao, Liufeng Tian, Miao Xie, Zhong Qiu, Qinjun Chen, Jianguo |
Author_xml | – sequence: 1 givenname: Qinjun surname: Qiu fullname: Qiu, Qinjun email: qiuqinjun@cug.edu.cn organization: Technology Innovation Center for Geological Data Intelligent Application, Department of Natural Resources of Jiangsu Province, 210012, China – sequence: 2 givenname: Xiangguo surname: Jin fullname: Jin, Xiangguo organization: National Engineering Research Center for Geographic Information System, Wuhan, Hubei 430074, China – sequence: 3 givenname: Miao surname: Tian fullname: Tian, Miao organization: Key Laboratory of Geological Survery and Evaluation of Ministry of Education, Wuhan, Hubei 430074, China – sequence: 4 givenname: Qirui surname: Wu fullname: Wu, Qirui organization: School of Computer and Science, China University of Geosciences, Wuhan, Hubei 430074, China – sequence: 5 givenname: Liufeng surname: Tao fullname: Tao, Liufeng organization: School of Computer and Science, China University of Geosciences, Wuhan, Hubei 430074, China – sequence: 6 givenname: Jianguo surname: Chen fullname: Chen, Jianguo organization: Key Laboratory of Geological Survery and Evaluation of Ministry of Education, Wuhan, Hubei 430074, China – sequence: 7 givenname: Zhong surname: Xie fullname: Xie, Zhong organization: School of Computer and Science, China University of Geosciences, Wuhan, Hubei 430074, China |
BookMark | eNqVkE1OwzAQhb0oEi1wBnyBFjupnWZZVfyqEhtYW248aV0SOxq7LbkHB8ZREVvEZmb0Zt4nzZuQkfMOCLnlbMYZl3f7mUfYQirHWcYykVQp52xExmlbTnkuF5dkEsKeMSYZ42Py9eKtixQ-I-oqWu9oC3HnDa09UnDRxp4iNHpYBVqjb2lrHaBukhz8ASsIaeo8xkATCbaYbt2WGujAGXBVTzuNYZC0M9S2HfojGJruuh2tvDv65jDQE9FBPHn8CNfkotZNgJuffkXeH-7fVk_T9evj82q5nlY5z-KUlxpyENkCtBESRM1ryeZZLuaSiU1tNnn6ut7oUjORF6Is5hshCi41YzoXmc6vyOLMPbhO9yfdNKpD22rsFWdqSFTt1W-iakhUnRNN1uJsrdCHgFD_w7k8OyF9drSAKlQ25QTGIlRRGW__ZHwDrlSfgg |
Cites_doi | 10.1111/tgis.12887 10.1109/ACCESS.2020.2996642 10.1609/aaai.v38i17.29919 10.1016/j.cageo.2024.105571 10.1016/j.oregeorev.2019.05.005 10.1007/s12145-019-00390-3 10.18653/v1/K18-2016 10.1007/s12583-022-1724-z 10.1016/j.autcon.2021.104108 10.1016/j.oregeorev.2021.104200 10.1007/s11004-023-10050-4 10.1016/j.ins.2021.10.047 10.1016/j.cageo.2022.105229 10.1007/s10115-020-01532-6 10.1007/s11430-020-9750-4 10.1029/2019EA000610 |
ContentType | Journal Article |
Copyright | 2025 The Author(s) |
Copyright_xml | – notice: 2025 The Author(s) |
DBID | 6I. AAFTH AAYXX CITATION ADTOC UNPAY |
DOI | 10.1016/j.oregeorev.2025.106640 |
DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef Unpaywall for CDI: Periodical Content Unpaywall |
DatabaseTitle | CrossRef |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: UNPAY name: Unpaywall url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/ sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Geology Engineering |
ExternalDocumentID | 10.1016/j.oregeorev.2025.106640 10_1016_j_oregeorev_2025_106640 S0169136825002008 |
GroupedDBID | --K --M .~1 0R~ 123 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 5VS 6I. 6OB 7-5 71M 8P~ 9JN AAEDT AAEDW AAFTH AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO AAYWO ABJNI ABMAC ABQEM ABQYD ABWVN ABXDB ACDAQ ACGFS ACLVX ACRLP ACRPL ACSBN ACVFH ADBBV ADCNI ADEZE ADMUD ADNMO ADVLN AEBSH AEIPS AEKER AENEX AEUPX AFJKZ AFPUW AFTJW AFXIZ AGCQF AGHFR AGQPQ AGRNS AGUBO AGYEJ AHHHB AIGII AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU APXCP ASPBG ATOGT AVWKF AZFZN BKOJK BLXMC BNPGV CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GROUPED_DOAJ HMA HVGLF HZ~ IHE IMUCA J1W KOM LY3 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SDF SDG SDP SEP SES SEW SPC SPCBC SSE SSH SSZ T5K WUQ XPP ZMT ~02 ~G- AAYXX ACLOT CITATION EFKBS EFLBG ~HD ADTOC UNPAY |
ID | FETCH-LOGICAL-c312t-19ae3e528ead56e5f1f6042354605bfdb3016fba9a05375974b55716a00a352a3 |
IEDL.DBID | .~1 |
ISSN | 0169-1368 1872-7360 |
IngestDate | Tue Aug 19 23:38:03 EDT 2025 Wed Oct 01 05:52:44 EDT 2025 Sat Jun 28 18:15:15 EDT 2025 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | Geological survey report Geological knowledge graph Graph convolutional network Geological entity relation extraction Dependent syntax |
Language | English |
License | This is an open access article under the CC BY license. cc-by |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c312t-19ae3e528ead56e5f1f6042354605bfdb3016fba9a05375974b55716a00a352a3 |
OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S0169136825002008 |
ParticipantIDs | unpaywall_primary_10_1016_j_oregeorev_2025_106640 crossref_primary_10_1016_j_oregeorev_2025_106640 elsevier_sciencedirect_doi_10_1016_j_oregeorev_2025_106640 |
ProviderPackageCode | CITATION AAYXX |
PublicationCentury | 2000 |
PublicationDate | July 2025 2025-07-00 |
PublicationDateYYYYMMDD | 2025-07-01 |
PublicationDate_xml | – month: 07 year: 2025 text: July 2025 |
PublicationDecade | 2020 |
PublicationTitle | Ore geology reviews |
PublicationYear | 2025 |
Publisher | Elsevier B.V |
Publisher_xml | – name: Elsevier B.V |
References | Enkhsaikhan, Liu, Holden (b0020) 2021; 63 Han, Wang (b0025) 2020; 8 Wei, Su, Wang (b0100) 2020 Qiao, Zou, Huang (b0055) 2022 Qiu, Xie, Wu (b0065) 2019; 12 Wang, Wu, Xie (b0095) 2022; 168 Yang, Li (b0110) 2024 Tian, Ma, Wu (b0090) 2024; 187 Zhou, Wang, Wang, Hou, Zheng, Shen, Cheng, Feng, Wang, Lv, Fan, Hu, Hou, Zhu (b0125) 2021; 64 Qiu, Wang, Xu (b0060) 2023; 29 Qi P., Dozat T., Zhang Y., et al., 2019. Universal dependency parsing from scratch. arXiv preprint arXiv:1901.10457. Holden, Liu, Horrocks (b0030) 2019; 111 Ma, Tian, Tan (b0040) 2023; 34 Qiu, Xie, Ma (b0075) 2022; 26 Wu, Lin, Leng (b0105) 2022; 135 Zeng, He, Zeng (b0120) 2019 Lu, Yu, Qiu (b0035) 2017; 19 Parsing (b0045) 2009 Enkhsaikhan, Liu, Holden (b0010) 2018 Zaratiana U, Tomeh N, Holat P, et al. An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction. Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(17): 19477-19487. Qiu, Ma, Lv (b0080) 2023; 55 Enkhsaikhan, Holden, Duuring (b0015) 2021; 135 Qiu, Xie, Wu (b0070) 2019; 6 Shang, Huang, Sun (b0085) 2022; 584 Bichri, Chergui, Hain (b0005) 2024; 15 Zhu, Tan, Wu (b0130) 2017; 26 Enkhsaikhan (10.1016/j.oregeorev.2025.106640_b0015) 2021; 135 Lu (10.1016/j.oregeorev.2025.106640_b0035) 2017; 19 Ma (10.1016/j.oregeorev.2025.106640_b0040) 2023; 34 10.1016/j.oregeorev.2025.106640_b0050 Wu (10.1016/j.oregeorev.2025.106640_b0105) 2022; 135 Holden (10.1016/j.oregeorev.2025.106640_b0030) 2019; 111 Qiu (10.1016/j.oregeorev.2025.106640_b0065) 2019; 12 Yang (10.1016/j.oregeorev.2025.106640_b0110) 2024 Zeng (10.1016/j.oregeorev.2025.106640_b0120) 2019 Tian (10.1016/j.oregeorev.2025.106640_b0090) 2024; 187 Bichri (10.1016/j.oregeorev.2025.106640_b0005) 2024; 15 Enkhsaikhan (10.1016/j.oregeorev.2025.106640_b0010) 2018 Parsing (10.1016/j.oregeorev.2025.106640_b0045) 2009 Wang (10.1016/j.oregeorev.2025.106640_b0095) 2022; 168 Qiu (10.1016/j.oregeorev.2025.106640_b0080) 2023; 55 Zhou (10.1016/j.oregeorev.2025.106640_b0125) 2021; 64 Zhu (10.1016/j.oregeorev.2025.106640_b0130) 2017; 26 Qiao (10.1016/j.oregeorev.2025.106640_b0055) 2022 10.1016/j.oregeorev.2025.106640_b0115 Qiu (10.1016/j.oregeorev.2025.106640_b0075) 2022; 26 Qiu (10.1016/j.oregeorev.2025.106640_b0070) 2019; 6 Qiu (10.1016/j.oregeorev.2025.106640_b0060) 2023; 29 Enkhsaikhan (10.1016/j.oregeorev.2025.106640_b0020) 2021; 63 Han (10.1016/j.oregeorev.2025.106640_b0025) 2020; 8 Shang (10.1016/j.oregeorev.2025.106640_b0085) 2022; 584 Wei (10.1016/j.oregeorev.2025.106640_b0100) 2020 |
References_xml | – volume: 64 start-page: 1105 year: 2021 end-page: 1114 ident: b0125 article-title: Geoscience knowledge graph in the big data era publication-title: Sci. China Earth Sci. – start-page: 224 year: 2018 end-page: 237 ident: b0010 article-title: Towards geological knowledge discovery using vector-based semantic similarity. International Conference on Advanced Data Mining and Applications – volume: 168 year: 2022 ident: b0095 article-title: Understanding geological reports based on knowledge graphs using a deep learning approach publication-title: Comput. Geosci. – year: 2019 ident: b0120 article-title: Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning. Empirical Methods in Natural Language Processing. Association for publication-title: Comput. Linguist. – year: 2024 ident: b0110 article-title: Entity Overlapping Relation Extracting Algorithm based on CNN and BERT publication-title: IEEE Access – volume: 15 year: 2024 ident: b0005 article-title: Investigating the Impact of Train/Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets publication-title: Int. J. Adv. Comput. Sci. Appl. – volume: 111 year: 2019 ident: b0030 article-title: GeoDocA–Fast analysis of geological content in mineral exploration reports: a text mining approach publication-title: Ore Geol. Rev. – volume: 63 start-page: 695 year: 2021 end-page: 715 ident: b0020 article-title: Auto-labelling entities in low-resource text: a geological case study publication-title: Knowl. Inf. Syst. – volume: 26 start-page: 839 year: 2022 end-page: 866 ident: b0075 article-title: Spatially oriented convolutional neural network for spatial relation extraction from natural language texts publication-title: Trans. GIS – volume: 135 year: 2022 ident: b0105 article-title: Rule-based information extraction for mechanical-electrical-plumbing-specific semantic web publication-title: Autom. Constr. – year: 2020 ident: b0100 article-title: A Novel Cascade Binary Tagging Framework for Relational Triple Extraction. Proceedings of the publication-title: 58th Annual Meeting of the Association for Computational Linguistics – volume: 34 start-page: 1390 year: 2023 end-page: 1405 ident: b0040 article-title: Ontology-based BERT model for automated information extraction from geological hazard reports publication-title: J. Earth Sci. – volume: 6 start-page: 931 year: 2019 end-page: 946 ident: b0070 article-title: GNER: A generative model for geological named entity recognition without labeled data using deep learning publication-title: Earth Space Sci. – reference: Qi P., Dozat T., Zhang Y., et al., 2019. Universal dependency parsing from scratch. arXiv preprint arXiv:1901.10457. – start-page: 1 year: 2022 end-page: 11 ident: b0055 article-title: A joint model for entity and relation extraction based on BERT publication-title: Neural Comput. Applic. – volume: 187 year: 2024 ident: b0090 article-title: Joint extraction of entity relations from geological reports based on a novel relation graph convolutional network publication-title: Comput. Geosci. – volume: 55 start-page: 423 year: 2023 end-page: 456 ident: b0080 article-title: Construction and application of a knowledge graph for iron deposits using text mining analytics and a deep learning algorithm publication-title: Math. Geosci. – reference: Zaratiana U, Tomeh N, Holat P, et al. An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction. Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(17): 19477-19487. – volume: 8 start-page: 96912 year: 2020 end-page: 96919 ident: b0025 article-title: A novel document-level relation extraction method based on BERT and entity information publication-title: IEEE Access – volume: 19 start-page: 723 year: 2017 end-page: 734 ident: b0035 article-title: On geographic knowledge graph publication-title: J. Geo-Informat. Sci. – volume: 26 year: 2017 ident: b0130 article-title: Research on semantic retrieval model towards geological big data publication-title: China Min. Mag. – volume: 584 start-page: 269 year: 2022 end-page: 279 ident: b0085 article-title: A pattern-aware self-attention network for distant supervised relation extraction publication-title: Inf. Sci. – year: 2009 ident: b0045 article-title: Speech and language processing publication-title: Power Point Slides – volume: 12 start-page: 565 year: 2019 end-page: 579 ident: b0065 article-title: BiLSTM-CRF for geological named entity recognition from the geoscience literature publication-title: Earth Sci. Inf. – volume: 29 start-page: 419 year: 2023 ident: b0060 article-title: 2023a. Research on the joint extraction method of entity relations in geological domain publication-title: Geol. J. China Univ. – volume: 135 year: 2021 ident: b0015 article-title: Understanding ore-forming conditions using machine reading of text publication-title: Ore Geol. Rev. – volume: 26 start-page: 839 issue: 2 year: 2022 ident: 10.1016/j.oregeorev.2025.106640_b0075 article-title: Spatially oriented convolutional neural network for spatial relation extraction from natural language texts publication-title: Trans. GIS doi: 10.1111/tgis.12887 – year: 2020 ident: 10.1016/j.oregeorev.2025.106640_b0100 article-title: A Novel Cascade Binary Tagging Framework for Relational Triple Extraction. Proceedings of the – volume: 29 start-page: 419 issue: 3 year: 2023 ident: 10.1016/j.oregeorev.2025.106640_b0060 article-title: 2023a. Research on the joint extraction method of entity relations in geological domain publication-title: Geol. J. China Univ. – volume: 19 start-page: 723 issue: 6 year: 2017 ident: 10.1016/j.oregeorev.2025.106640_b0035 article-title: On geographic knowledge graph publication-title: J. Geo-Informat. Sci. – volume: 8 start-page: 96912 year: 2020 ident: 10.1016/j.oregeorev.2025.106640_b0025 article-title: A novel document-level relation extraction method based on BERT and entity information publication-title: IEEE Access doi: 10.1109/ACCESS.2020.2996642 – start-page: 1 year: 2022 ident: 10.1016/j.oregeorev.2025.106640_b0055 article-title: A joint model for entity and relation extraction based on BERT publication-title: Neural Comput. Applic. – ident: 10.1016/j.oregeorev.2025.106640_b0115 doi: 10.1609/aaai.v38i17.29919 – volume: 187 year: 2024 ident: 10.1016/j.oregeorev.2025.106640_b0090 article-title: Joint extraction of entity relations from geological reports based on a novel relation graph convolutional network publication-title: Comput. Geosci. doi: 10.1016/j.cageo.2024.105571 – volume: 111 year: 2019 ident: 10.1016/j.oregeorev.2025.106640_b0030 article-title: GeoDocA–Fast analysis of geological content in mineral exploration reports: a text mining approach publication-title: Ore Geol. Rev. doi: 10.1016/j.oregeorev.2019.05.005 – start-page: 224 year: 2018 ident: 10.1016/j.oregeorev.2025.106640_b0010 – volume: 12 start-page: 565 year: 2019 ident: 10.1016/j.oregeorev.2025.106640_b0065 article-title: BiLSTM-CRF for geological named entity recognition from the geoscience literature publication-title: Earth Sci. Inf. doi: 10.1007/s12145-019-00390-3 – ident: 10.1016/j.oregeorev.2025.106640_b0050 doi: 10.18653/v1/K18-2016 – volume: 34 start-page: 1390 issue: 5 year: 2023 ident: 10.1016/j.oregeorev.2025.106640_b0040 article-title: Ontology-based BERT model for automated information extraction from geological hazard reports publication-title: J. Earth Sci. doi: 10.1007/s12583-022-1724-z – volume: 135 year: 2022 ident: 10.1016/j.oregeorev.2025.106640_b0105 article-title: Rule-based information extraction for mechanical-electrical-plumbing-specific semantic web publication-title: Autom. Constr. doi: 10.1016/j.autcon.2021.104108 – volume: 15 issue: 2 year: 2024 ident: 10.1016/j.oregeorev.2025.106640_b0005 article-title: Investigating the Impact of Train/Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets publication-title: Int. J. Adv. Comput. Sci. Appl. – volume: 135 year: 2021 ident: 10.1016/j.oregeorev.2025.106640_b0015 article-title: Understanding ore-forming conditions using machine reading of text publication-title: Ore Geol. Rev. doi: 10.1016/j.oregeorev.2021.104200 – volume: 55 start-page: 423 issue: 3 year: 2023 ident: 10.1016/j.oregeorev.2025.106640_b0080 article-title: Construction and application of a knowledge graph for iron deposits using text mining analytics and a deep learning algorithm publication-title: Math. Geosci. doi: 10.1007/s11004-023-10050-4 – year: 2024 ident: 10.1016/j.oregeorev.2025.106640_b0110 article-title: Entity Overlapping Relation Extracting Algorithm based on CNN and BERT publication-title: IEEE Access – year: 2009 ident: 10.1016/j.oregeorev.2025.106640_b0045 article-title: Speech and language processing publication-title: Power Point Slides – volume: 584 start-page: 269 year: 2022 ident: 10.1016/j.oregeorev.2025.106640_b0085 article-title: A pattern-aware self-attention network for distant supervised relation extraction publication-title: Inf. Sci. doi: 10.1016/j.ins.2021.10.047 – volume: 168 year: 2022 ident: 10.1016/j.oregeorev.2025.106640_b0095 article-title: Understanding geological reports based on knowledge graphs using a deep learning approach publication-title: Comput. Geosci. doi: 10.1016/j.cageo.2022.105229 – year: 2019 ident: 10.1016/j.oregeorev.2025.106640_b0120 article-title: Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning. Empirical Methods in Natural Language Processing. Association for publication-title: Comput. Linguist. – volume: 26 issue: 12 year: 2017 ident: 10.1016/j.oregeorev.2025.106640_b0130 article-title: Research on semantic retrieval model towards geological big data publication-title: China Min. Mag. – volume: 63 start-page: 695 issue: 3 year: 2021 ident: 10.1016/j.oregeorev.2025.106640_b0020 article-title: Auto-labelling entities in low-resource text: a geological case study publication-title: Knowl. Inf. Syst. doi: 10.1007/s10115-020-01532-6 – volume: 64 start-page: 1105 issue: 7 year: 2021 ident: 10.1016/j.oregeorev.2025.106640_b0125 article-title: Geoscience knowledge graph in the big data era publication-title: Sci. China Earth Sci. doi: 10.1007/s11430-020-9750-4 – volume: 6 start-page: 931 issue: 6 year: 2019 ident: 10.1016/j.oregeorev.2025.106640_b0070 article-title: GNER: A generative model for geological named entity recognition without labeled data using deep learning publication-title: Earth Space Sci. doi: 10.1029/2019EA000610 |
SSID | ssj0006001 |
Score | 2.4268472 |
Snippet | [Display omitted]
•Propose a GCN entity relationship joint extraction model based on dependency syntax analysis.•Propose a GCN with stacked pointer networks to... |
SourceID | unpaywall crossref elsevier |
SourceType | Open Access Repository Index Database Publisher |
StartPage | 106640 |
SubjectTerms | Dependent syntax Geological entity relation extraction Geological knowledge graph Geological survey report Graph convolutional network |
SummonAdditionalLinks | – databaseName: Unpaywall dbid: UNPAY link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1dS8MwFA1jQ8QHP6biROU--NrZrk3W-jbEOQaOPTiYTyXpUpjOdnQdUn-HP9ibph2bKH68FpK0yW1ybu655xJy6bQplbbjGVy2J4bjtkJDuIFtBIiNJPVcKfIL_fsB642c_piOK-SqzIXZiN_nPKw4Qfc5VgVZ0E-n-JQxB330GlMRpSqpjQbDzqNW8PYMy9bJb24bcaPNzA1G15c9fXcebS-jOc9e-Wy2dt5098iwfFNNM3luLlPRDN4-iTj-4VP2yW6BPaGjjeWAVGRUJztrioR1snWXV_rNDsl7P55GKeDenejcB9DFpgFRLuTJvRkkJZMOVJYKvExzCWt8rEMCCygiElCKUuAYUJbdDTKY8_yqAng0gWl-uyEnkEtog2LDF38F9hhpsvriiIy6tw83PaMo4WAEttVKDcvj0pa05aLBUiZpaIVMMXGoCseKcCJwf2Gh4B5XujLKuRGUogvHTZMjNOT2MalGcSRPCISKSIInbiBF6HgOdUMaIDziLrqoqtxwg5jlQvpzrdThlxS2J3819b6ael9PfYNclwvuF4BDAwkf1-7nxtbKRH474Ok_2pyRapos5Tlin1RcFPb-AUG0BWo priority: 102 providerName: Unpaywall |
Title | Joint extraction method for entity relations from mineral resources reports integrating dependency parsing and improved graph convolutional networks |
URI | https://dx.doi.org/10.1016/j.oregeorev.2025.106640 https://doi.org/10.1016/j.oregeorev.2025.106640 |
UnpaywallVersion | publishedVersion |
Volume | 182 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals issn: 0169-1368 databaseCode: DOA dateStart: 20220101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.doaj.org/ omitProxy: true ssIdentifier: ssj0006001 providerName: Directory of Open Access Journals – providerCode: PRVESC databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier) issn: 0169-1368 databaseCode: GBLVA dateStart: 20110101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: true ssIdentifier: ssj0006001 providerName: Elsevier – providerCode: PRVESC databaseName: Elsevier ScienceDirect issn: 0169-1368 databaseCode: ACRLP dateStart: 20220101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: true ssIdentifier: ssj0006001 providerName: Elsevier – providerCode: PRVESC databaseName: ScienceDirect Freedom Collection 2013 issn: 0169-1368 databaseCode: .~1 dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: true ssIdentifier: ssj0006001 providerName: Elsevier – providerCode: PRVESC databaseName: ScienceDirect Freedom Collection Journals issn: 0169-1368 databaseCode: AIKHN dateStart: 20220101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: true ssIdentifier: ssj0006001 providerName: Elsevier – providerCode: PRVLSH databaseName: Elsevier Journals issn: 0169-1368 databaseCode: AKRWK dateStart: 19950501 customDbUrl: isFulltext: true mediaType: online dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0006001 providerName: Library Specific Holdings |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEF5KRdSDaFWsjzIHr7FNk00Tb6VYq2IRtFBPYZNsIFLTkrZIL_4Kf7Azu0ltQVDwmCXJhswwr_3mG8Yu7Bbn0rI9Q8hWZNhuMzYCN7SMEGMjyT1XBqqg_9B3egP7bsiHJdYpemEIVpnbfm3TlbXOV-r536xPkqT-RDwipuVgikMxj2r4JfYv1OnLj2-YBzl0ze_tGXT3GsZrnGFqPqZhL030_bjqOFQF-dlDbc3TiVi8i9FoxQN199huHjpCW3_dPivJtMJ2VggFK2zzRg3qXRywz7txks4ATW-mWxdAz4oGDFJB9eYuICuAcEBNJvCWKAZqXNYV_SnkBwpQcErgHlBMzQ0XMBGq0gAijSBRxQkZgWLABgKz50qNb0w11nx6yAbd6-dOz8gnMBihZTZnhukJaUnedFHfuCN5bMYOAWk4naYGcRSgeXDiQHiCaGEoNwk4xwxMNBoCIzthHbFyOk7lMYOYcCDoMEMZxLZnczfmIUY3wsUMk6YFV1mj-Ov-RBNt-AUC7dVfCsonQflaUFV2VUjHX9MZH93B7w-bS3n-dcOT_2x4yrbpSkN9z1h5ls3lOQY0s6CmNLbGNtq3971-TZUF8GrQf2y_fAEItfxW |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB6kRdSDaFV8OwevoU2TjYm3Uqytj15sobewSTcQ0STEFsn_8Ac7k02KgqDgdcNmQ2aY137zDcClfSWEsmzPkOpqbthuNzICN7SMkGIjJTxXBWVB_3HsDKf23UzM1qBf98IwrLKy_dqml9a6WmlXf7OdxXH7iXlETMuhFIdjHm74bdqCbHIDmr3R_XC8Msjs0zXFt2fwhm8wrzSn7DzleS9dcv-06jhcCPnZSW0sk0wW7_Ll5YsTGuzAdhU9Yk9_4C6sqaQFW184BVuwflvO6i324OMujZMFkvXNdfcC6nHRSHEqlu25BeY1Fg65zwRf45KEmpZ1Uf8NqzsFrGkl6AysB-eGBWayLDagTOYYl_UJNceSBBsZz17pNb0x0XDzt32YDm4m_aFRDWEwQsvsLgzTk8pSouuSyglHiciMHMbSCL5QDaJ5QBbCiQLpSWaG4fQkEIKSMNnpSArupHUAjSRN1CFgxFAQ8pmhCiLbs4UbiZACHOlSkskDg4-gU_91P9NcG34NQnv2V4LyWVC-FtQRXNfS8b-pjU8e4ffN5kqefz3w-D8HXsDGcPL44D-MxvcnsMlPNPL3FBqLfKnOKL5ZBOeV_n4CwVr8XA |
linkToUnpaywall | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1dS8MwFA1jQ8QHP6biROU--NrZrk3W-jbEOQaOPTiYTyXpUpjOdnQdUn-HP9ibph2bKH68FpK0yW1ybu655xJy6bQplbbjGVy2J4bjtkJDuIFtBIiNJPVcKfIL_fsB642c_piOK-SqzIXZiN_nPKw4Qfc5VgVZ0E-n-JQxB330GlMRpSqpjQbDzqNW8PYMy9bJb24bcaPNzA1G15c9fXcebS-jOc9e-Wy2dt5098iwfFNNM3luLlPRDN4-iTj-4VP2yW6BPaGjjeWAVGRUJztrioR1snWXV_rNDsl7P55GKeDenejcB9DFpgFRLuTJvRkkJZMOVJYKvExzCWt8rEMCCygiElCKUuAYUJbdDTKY8_yqAng0gWl-uyEnkEtog2LDF38F9hhpsvriiIy6tw83PaMo4WAEttVKDcvj0pa05aLBUiZpaIVMMXGoCseKcCJwf2Gh4B5XujLKuRGUogvHTZMjNOT2MalGcSRPCISKSIInbiBF6HgOdUMaIDziLrqoqtxwg5jlQvpzrdThlxS2J3819b6ael9PfYNclwvuF4BDAwkf1-7nxtbKRH474Ok_2pyRapos5Tlin1RcFPb-AUG0BWo |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Joint+extraction+method+for+entity+relations+from+mineral+resources+reports+integrating+dependency+parsing+and+improved+graph+convolutional+networks&rft.jtitle=Ore+geology+reviews&rft.au=Qiu%2C+Qinjun&rft.au=Jin%2C+Xiangguo&rft.au=Tian%2C+Miao&rft.au=Wu%2C+Qirui&rft.date=2025-07-01&rft.pub=Elsevier+B.V&rft.issn=0169-1368&rft.volume=182&rft_id=info:doi/10.1016%2Fj.oregeorev.2025.106640&rft.externalDocID=S0169136825002008 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0169-1368&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0169-1368&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0169-1368&client=summon |