A semantic similarity-based method for semi-automated IFC exension Zhang, Jiansong; El-Gohary, Nora
The Industry Foundation Classes (IFC) schema was designed as a comprehensive data schema to cover information of all phases of a building project and all disciplines of the AEC industry. But due to its limited coverage of details in certain subdomains, the IFC schema needs to be extended for many information processing tasks such as information extraction for automated regulatory compliance checking. Previous IFC extension efforts typically extended IFC in an ad-hoc and subjective manner. A more objective, standardized, and application-independent method for extending IFC is, thus, needed. To address this gap, a new method for extending the IFC schema objectively and semi-automatically is proposed. The proposed method utilizes a semantic relation-based concept matching algorithm to find concepts – from domain documents – to incorporate into the current IFC schema class hierarchy. It utilizes the hypernymy, hyponymy, and synonymy semantic relations. This paper focuses on presenting the proposed semantic relation-based concept matching algorithm: the ZESeM (Zhang and El-Gohary Semantic Matching) algorithm. The ZESeM algorithm was tested on processing concepts from Chapter 12 of the International Building Code 2006. Different semantic similarity computation methods were tested in combination with the proposed ZESeM algorithm. The ZESeM algorithm was evaluated based on adoption rate, which is the number of concepts found by the ZESeM algorithm that are adopted divided by the total number of concepts found by the ZESeM algorithm. An adoption rate of 85.8% was achieved. The proposed semantic relation-based concept matching algorithm offers a more efficient concept matching method for semi-automatically extending the IFC schema.
Item Citations and Data
Attribution-NonCommercial-NoDerivs 2.5 Canada