Bridging building information systems: A parameter-efficient semantic approach to construction data interoperability

This study investigates the application of semantic text similarity embedding models to address data interoperability challenges in the construction and civil engineering sectors. Research focuses on improving embedding models to produce domain-specific embeddings that precisely capture the complex terminology and relationships among various building systems, including Building Information Modeling, Building Energy Modeling, and Building Management Systems. In this study, we explored the use of embedding models to enhance semantic text similarity applications within the construction industry. The aim is to augment general-purpose language models by training them on a comprehensive construction and civil engineering data corpus to promote enhanced data integration and interoperability among diverse sources. Our methodology includes a comprehensive data collection and preprocessing pipeline, followed by a multi-stage fine-tuning approach that employs continuous pre-training, task-specific fine-tuning, and parameter-efficient adaptation algorithms. We assess the effectiveness of our models through intrinsic evaluations, including semantic similarity measures and domain-specific benchmarks. The test results demonstrate that our domain-adapted models, especially the Weight-Decomposed Low-Rank Adaptation method, substantially surpass the fundamental language models in domain-specific tasks, including understanding technical terms and data alignment across domains. The results of the models show significant performance enhancements with minimal resource investment, making them appropriate for practical use. Our research demonstrates that domain-specific embedding models can substantially improve data integration and enable more advanced, data-driven applications in the building industry.