||AUTOMATED INFORMATION EXTRACTION FROM CONSTRUCTION-RELATED REGULATORY DOCUMENTS FOR AUTOMATED COMPLIANCE CHECKING
||J Zhang, N El-Gohary
||Manual regulatory compliance checking is usually time-consuming, costly, and error-prone. Automating the process of compliance checking is expected to reduce the time and cost of the process, as well as reduce the probability of making compliance assessment errors. One aspect of automating the compliance checking process is automating the extraction of information (rules that the project needs to comply with) from construction-related regulatory documents (which are expressed in textual format). With the advancements in the artificial intelligence domain, natural language processing (NLP) techniques are being widely used in many fields for information extraction from unstructured text. There have been few research efforts to apply NLP techniques in the construction domain. However, none of these efforts attempted to automatically extract rules from textual regulatory documents. In this paper, the authors propose an approach for semantic information extraction (using domain-specific meaning, in addition to syntax-related text features) to automatically extract information from construction-related regulatory documents and represent it in a computer-understandable, structured format. Preliminary experimental results are presented and discussed in the paper.
|Year of publication:
||Compliance Checking, Natural Language Processing, Information Extraction, Artificial Intelligence, Automation
J Zhang, N El-Gohary (2011).
AUTOMATED INFORMATION EXTRACTION FROM CONSTRUCTION-RELATED REGULATORY DOCUMENTS FOR AUTOMATED COMPLIANCE CHECKING . Proceedings of the 28th International Conference of CIB W78, Sophia Antipolis, France, 26-28 October,