Automated Relation Extraction for Improved Generalizability across Different Types of Text
Publication: Computing in Civil Engineering 2023
ABSTRACT
Bridge textual reports capture technically detailed data/information about bridge conditions and maintenance actions, which offers opportunities to improve the prediction of future bridge conditions for further bridge maintenance decision-making support. To automatically analyze these reports, there is a need for relation extraction methods to extract relation information from the reports for linking recognized entities with predefined semantic categories (e.g., caused by) and representing the extracted semantic relations in a structured way. To address this need, this paper proposes a deep learning-based relation extraction model. The proposed model utilizes convolutional neural network (CNN) to encode sentence-level features, and bidirectional long short-term memory (BiLSTM) to build a relation extractor to capture the patterns of the predefined relation types. The proposed model was evaluated in extracting relations from multiple types of bridge-related textual reports for representing bridge defect information—including relations among bridge entities—in a semantically rich structured way.
Get full access to this article
View all available purchase options and get full access to this chapter.
REFERENCES
Akanbi, T., and Zhang, J. (2021). “Design information extraction from construction specifications to support cost estimation.” Automation in Construction, 131, 1–14.
ASCE. (2020). Report card for America’s infrastructure, https://infrastructurereportcard.org/wp-content/uploads/2020/12/Bridges-2021.pdf.
Bhatia, P., Celikkaya, B., Khalilia, M., and Senthivel, S. (2019). “Comprehend medical: A named entity recognition and relationship extraction web service.” Proc., 18th IEEE International Conference on Machine Learning and Applications, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, 1844–1851.
Chen, L., et al. (2020). “A deep learning based method for extracting semantic information from patent documents.” Advanced Engineering Informatics, 43, 289–312.
Frangopol, D. M., Dong, Y., and Sabatino, S. (2017). “Bridge life-cycle performance and cost: analysis, prediction, optimisation and decision-making.” Structure and Infrastructure Engineering, 13(10), 1239–1257.
Li, T., Alipour, M., and Harris, D. K. (2021). “Context-aware sequence labeling for condition information extraction from historical bridge inspection reports.” Advanced Engineering Informatics, 49, 1–16.
Liu, K., and El-Gohary, N. (2021). “Semantic neural network ensemble for automated dependency relation extraction from bridge inspection reports.” Journal of Computing in Civil Engineering, 35(4).
Miwa, M., and Bansal, M. (2016). “End-to-end relation extraction using LSTMs on sequences and tree structures.”.
Pouran Ben Veyseh, A., Dernoncourt, F., Dou, D., and Nguyen, T. H. (2020). “Exploiting the syntax-model consistency for neural relation extraction.” Proc., 58th Annual Meeting of the Association for Computational Linguistics, MIT Press, Cambridge, MA, 8021–8032.
Staudemeyer, R. C., and Morris, E. R. (2019). “Understanding LSTM-a tutorial into long short-term memory recurrent neural networks.”.
Wang, X., and El-Gohary, N. (2023). “Deep learning-based relation extraction and knowledge graph-based representation of construction safety requirements.” Automation in Construction, 147, 1–16.
Yan, C., Fu, X., Wu, W., Lu, S., and Wu, J. (2019). “Neural network based relation extraction of enterprises in credit risk management.” Proc., 2019 IEEE International Conference on Big Data and Smart Computing, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, 1–6.
Yao, Y., Ye, D., Li, P., Han, X., Lin, Y., Liu, Z., Liu, Z., Huang, L., Zhou, J., and Sun, M. (2019). “DocRED: A large-scale document-level relation extraction dataset.”.
Zhang, J., and El-Gohary, N. M. (2013). “Semantic NLP-based information extraction from construction regulatory documents for automated compliance checking.” Journal of Computing in Civil Engineering, 30(2), 1–14.
Zhang, Y., Lin, H., Yang, Z., Wang, J., Zhang, S., Sun, Y., and Yang, L. (2018). “A hybrid model based on neural networks for biomedical relation extraction.” Journal of Biomedical Informatics, 81, 83–92.
Information & Authors
Information
Published In
Computing in Civil Engineering 2023
Pages: 451 - 458
History
Published online: Jan 25, 2024
ASCE Technical Topics:
- Architectural engineering
- Artificial intelligence and machine learning
- Automation and robotics
- Bridge engineering
- Bridge management
- Bridge tests
- Building information modeling
- Building management
- Business management
- Computer programming
- Computing in civil engineering
- Decision making
- Engineering fundamentals
- Field tests
- Maintenance and operation
- Neural networks
- Practice and Profession
- Structural analysis
- Structural engineering
- Systems engineering
- Tests (by type)
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.