Name
Title | ||
|---|---|---|
Understanding geological reports based on knowledge graphs using a deep learning approach |
Abstract | ||
|---|---|---|
Geological reports aid in understanding exploration by providing valuable information on rock formation ,evolution and the geological environment in which deposits formed. Querying and extracting the critical information from these enormous historical geological report data helps in understanding the exploration risks in different geological settings. However, large amounts of unstructured text data occur in geological reports; therefore, it is challenging to obtain valuable information from them without performing information extraction and processing. This study proposed an automated method for extracting information from geological reports through triple extraction, then automatically constructs a geological knowledge graph from the extracted entities and relations. Simultaneously, due to the lack of samples, this study used multiple geological reports to construct a corpus of jointly extracted geological entities and relations. The proposed model reached an F1-score of 90.05% in the experimental results on the constructed corpus. Finally, a knowledge graph was constructed based on the extracted results to demonstrate the application value of the proposed method. The results showed that the structured information helps better represent the content of the source report and matches well with the geological domain knowledge. The proposed method can quickly and robustly convert textual data into a structured form that is convenient for reasoning and querying geological entities and relations. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1016/j.cageo.2022.105229 | Computers & Geosciences |
Keywords | DocType | Volume |
Geological reports,Geological entities and relations,Deep learning,Geological knowledge graphs | Journal | 168 |
ISSN | Citations | PageRank |
0098-3004 | 0 | 0.34 |
References | Authors | |
0 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bin Wang | 1 | 1788 | 246.68 |
| Liang Wu | 2 | 0 | 0.34 |
| Zhong Xie | 3 | 34 | 12.55 |
| Qinjun Qiu | 4 | 0 | 0.34 |
| Yuan Zhou | 5 | 0 | 0.34 |
| Kai Ma | 6 | 0 | 0.34 |
| Liufeng Tao | 7 | 0 | 0.34 |