Extraction of construction regulatory requirements from textual documents using natural language processing techniques

Automated regulatory compliance checking requires automated information extraction (IE) from regulatory textual documents (e.g. building codes). Automated IE is a challenging task that requires complex processing of text. Natural Language Processing (NLP) aims at enabling computers to process natural language text in a human-like manner using a variety of text processing techniques, such as phrase-structure parsing, dependency parsing, etc. This paper proposes a hybrid syntactic (syntax/grammar-related) and semantic (meaning/context-related) NLP approach for automated IE from construction regulatory documents, and explores the use of two techniques (phrase-structure grammar and dependency grammar) for extracting information from complex sentences. IE rules were developed based on Chapter 12 of the 2006 International Building Code; and the approach was tested on Chapter 12 of the 2009 International Fire Code. Initial experimental results are presented, empirically evaluated in terms of precision and recall, and discussed.