Application of NLP Technology in the Information Extraction of Bridge Management and Maintenance Documents
|
|
|||||||||||
Bibliographic Details
| Author(s): |
Lu-yang Zhang
(Department of Bridge Engineering, Tongji University, Shanghai 200092, China)
Ye Xia (Department of Bridge Engineering, Tongji University, Shanghai 200092, China) Limin Sun 
(State Key Laboratory for Disaster Reduction in Civil Engineering, Tongji University, Shanghai, 200092, China)
|
||||
|---|---|---|---|---|---|
| Medium: | conference paper | ||||
| Language(s): | English | ||||
| Conference: | IABSE Congress: Bridges and Structures: Connection, Integration and Harmonisation, Nanjing, People's Republic of China, 21-23 September 2022 | ||||
| Published in: | IABSE Congress Nanjing 2022 | ||||
|
|||||
| Page(s): | 1224-1230 | ||||
| Total no. of pages: | 7 | ||||
| DOI: | 10.2749/nanjing.2022.1224 | ||||
| Abstract: |
Bridge management and maintenance document is the accumulation of authoritative technical data to record the history of bridge operation, current technical status and management and maintenance process, which contains substantial information to support bridge maintenance decision. With more and more extensive application of bridge health monitoring in civil engineering industry, bridge management and maintenance documents become more common and quantitative. Therefore, a large number of these reports need to be manually read and analyzed to obtain effective information, which will waste a lot of effort. In order to improve this situation, this paper develops a frequency state analyzer using LSTM neural network to classify these documents automatically, and improve the efficiency of bridge management and maintenance work. |
||||
| Keywords: |
LSTM natural language processing bridge management and maintenance documents text categorization
|
||||
| Copyright: | © 2022 International Association for Bridge and Structural Engineering (IABSE) | ||||
| License: | This creative work is copyrighted material and may not be used without explicit approval by the author and/or copyright owner. |
||||