English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We introduce the first automated models for classifying natural languagedescriptions provided in cost documents called "Bills of Quantities" (BoQs)popular in the infrastructure construction industry, into the InternationalConstruction Measurement Standard (ICMS). The models we deployed andsystematically evaluated for multi-class text classification are learnt from adataset of more than 50 thousand descriptions of items retrieved from 24 largeinfrastructure construction projects across the United Kingdom. We describe ourapproach to language representation and subsequent modelling to examine thestrength of contextual semantics and temporal dependency of language used inconstruction project documentation. To do that we evaluate two experimentalpipelines to inferring ICMS codes from text, on the basis of two differentlanguage representation models and a range of state-of-the-art sequence-basedclassification methods, including recurrent and convolutional neural networkarchitectures. The findings indicate a highly effective and accurate ICMSautomation model is within reach, with reported accuracy results above 90% F1score on average, on 32 ICMS categories. Furthermore, due to the specificnature of language use in the BoQs text; short, largely descriptive andtechnical, we find that simpler models compare favourably to achieving higheraccuracy results. Our analysis suggest that information is more likely embeddedin local key features in the descriptive text, which explains why a simplergeneric temporal convolutional network (TCN) exhibits comparable memory torecurrent architectures with the same capacity, and subsequently outperformsthese at this task.

A Machine Learning Approach to Classifying Construction Cost Documents into the International Construction Measurement Standard