EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BERT-Based Schema Matching for Integrating Heterogeneous Flood Data: A Case Study in Korea

Taeyoung Choe, Mincheol Shin, Kwangyoung Kim, Myungseok Yang, Ka Lok Man, Mucheol Kim

Systems · 02.03.2026 · 14 (3) · 267

DOI: 10.3390/systems14030267 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Systems, online erschienen am 02.03.2026. Verfasst von Taeyoung Choe und 5 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Institute of Information & Communications Technology Planning & Evaluation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Integrating flood-response datasets across municipalities is often hindered by heterogeneous and non-standard variable names, a challenge amplified in Korean by local naming conventions and linguistic variation. This study addresses scalable schema alignment to standardize municipal flood datasets with reduced manual effort while maintaining semantic consistency for downstream modeling. We propose a BERT-based schema matching framework that augments standardized attribute names with paraphrases generated by a generative language model and filtered to reduce semantic drift. Both standardized and target variable names are encoded using a flood-domain-adapted Korean BERT model, and candidate correspondences are retrieved via cosine-similarity ranking to produce top-k match suggestions for automated or human-in-the-loop alignment. Experiments on real flood-related tables from Busan and Incheon, evaluated jointly to diversify variable expressions, show that augmentation substantially improves top-k retrieval accuracy. In the combined evaluation, Hit@5 improves from 0.71 to 0.95, supporting more reliable schema harmonization for simulation-ready inputs.

Förderung

  • National Research Foundation of Korea
  • Institute of Information & Communications Technology Planning & Evaluation

Zitieren

APA

Choe, T., Shin, M., Kim, K., Yang, M., Man, K. L., & Kim, M. (2026). BERT-Based Schema Matching for Integrating Heterogeneous Flood Data: A Case Study in Korea. Systems, 14(3), 267. https://doi.org/10.3390/systems14030267

Vancouver

Choe T, Shin M, Kim K, Yang M, Man KL, Kim M. BERT-Based Schema Matching for Integrating Heterogeneous Flood Data: A Case Study in Korea. Systems. 2026;14(3):267. doi:10.3390/systems14030267

BibTeX
@article{Choe2026,
  author = {Choe, Taeyoung and Shin, Mincheol and Kim, Kwangyoung and Yang, Myungseok and Man, Ka Lok and Kim, Mucheol},
  title = {BERT-Based Schema Matching for Integrating Heterogeneous Flood Data: A Case Study in Korea},
  journal = {Systems},
  year = {2026},
  volume = {14},
  number = {3},
  pages = {267},
  doi = {10.3390/systems14030267}
}
Kostenlos starten →