Semantic text-pairing for relevant provision identification in construction specification reviews.

Field engineers should manually analyze the site appropriateness of every provision in a construction specification by comparing the requirements against the national standards. To support the manual review involving multiple documents, the authors proposed a semantic text-pairing method that identified relevant provisions from different specifications considering the textual properties. First, 2527 provisions were prepared from two construction specifications of highway projects undertaken in Qatar and five national standards from Australia, the United Kingdom, and the United States. Second, the Doc2Vec model trained the provisions and learned the textual features based on Paragraph Vector with Distributed Memory. Third, the provision relevance was estimated by normalizing cosine similarities between provision vectors generated by the Doc2Vec model. The experiments returned promising results, with an average matching accuracy of 84.40%. The results contribute to the specification review by automatically identifying the most relevant provisions and making the process objective and robust to human errors. • The provision pairing model achieved 84.4% matching accuracy. • The model learned semantic textual features from differently organized provisions. • The model made specification review quick, objective, and robust to human errors. • First attempt to analyze different properties of multiple construction specifications. [ABSTRACT FROM AUTHOR]