Concept Relation Extraction from Construction Documents Using Natural Language Processing

The objective of this research is to present an innovative technique for managing the knowledge contained in construction contract documents to facilitate quick access and efficient use of such knowledge for project management and contract administration tasks. Knowledge Management has become the focus of a lot of scientific research during the second half of the 20th century as researchers discovered the importance of the knowledge resource to business organizations. Despite early expectations of improved document management techniques, document management systems used in the construction industry have failed to deliver the anticipated performance. Recent research attempts to utilize analysis of the contents of documents to improve document categorization and retrieval functions. It is hypothesized that natural language processing can be effectively used to perform document text analysis. The proposed system, technique for concept relation identification using shallow parsing (CRISP), utilizes a shallow parser to extract semantic knowledge from construction contract documents which can be used to improve electronic document management functions such as document categorization and retrieval. When compared with human evaluators, CRISP achieved almost 80% of the average kappa score attained by the evaluators, and approximately 90% of their F-measure score.