Evaluation of Seven Part-of-Speech Taggers in Tagging Building Codes: Identifying the Best Performing Tagger and Common Sources of Errors

Xue, Xiaorui; Zhang, Jiansong

doi:10.1061/9780784482865.053

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…O gold standard consiste no conjunto de trechos selecionados da LOUOS usados no experimento e suas respectivas tags, que foram posteriormente checadas manualmente por dois avaliadores. A abordagem para o desenvolvimento do gold standard foi baseada em [16], e está dividida em três etapas: etiquetagem dos tokens pelo POS-tagger; avaliação do resultado pelo primeiro avaliador, um discente de graduação em Letras na Universidade Federal do Rio de Janeiro (UFRJ), e por último, por nova avaliação por uma pós-graduada em letras da Universidade Federal da Bahia (UFBA). Durante as avaliações, as tags que foram consideradas pelos avaliadores como incorretamente atribuídas foram sinalizadas, e as tags corretas explicitadas.…”

Section: Entac2022 -Ambiente Construído: Resiliente E Sustentávelunclassified

Processamento de Linguagem Natural (PLN) para automatização da checagem de conformidade:

Ávila¹,

Brito²,

Santos³

et al. 2022

Xix Encontro Nacional De Tecnologia Do Ambiente Construído

View full text Add to dashboard Cite

A checagem manual de conformidade de projetos é uma tarefa custosa e sujeita a erros. Os parâmetros contidos nos códigos regulatórios podem ser automaticamente extraídos usando o Processamento de Linguagem Natural (PLN), tornando a checagem mais eficiente e segura. Este estudo investiga uma rotina utilizando técnicas de PLN para o pré-processamento – primeira etapa para extração de informação - de um código regulatório urbanístico brasileiro. Utilizou-se no experimento a linguagem de programação Python e a biblioteca Natural Language Tool Kit (NLTK). Obteve-se uma acurácia de 68% no desempenho do etiquetador, indicando a necessidade de aprimoramentos no pré-processamento para a língua portuguesa.

show abstract

Section: Entac2022 -Ambiente Construído: Resiliente E Sustentávelunclassified

Processamento de Linguagem Natural (PLN) para automatização da checagem de conformidade:

Ávila¹,

Brito²,

Santos³

et al. 2022

Xix Encontro Nacional De Tecnologia Do Ambiente Construído

View full text Add to dashboard Cite

show abstract

“…To this end, the architectural engineering and construction (AEC) industry can rely on recent artificial intelligence (AI) developments, using machine learning (ML) and natural language processing (NLP) methods to perform budget probabilistic analyses and predictions based on large amounts of data that would be impossible for humans to leverage properly otherwise (Juszczyk, 2018a(Juszczyk, , 2018bElmousalami, 2020a;Xue and Zhang, 2020).…”

Section: Introductionmentioning

confidence: 99%

Automation of text document classification in the budgeting phase of the Construction process: a Systematic Literature Review

Jacques de Sousa,

Poças Martins,

Sanhudo

et al. 2024

View full text Add to dashboard Cite

Purpose This study aims to review recent advances towards the implementation of ANN and NLP applications during the budgeting phase of the construction process. During this phase, construction companies must assess the scope of each task and map the client’s expectations to an internal database of tasks, resources and costs. Quantity surveyors carry out this assessment manually with little to no computer aid, within very austere time constraints, even though these results determine the company’s bid quality and are contractually binding. Design/methodology/approach This paper seeks to compile applications of machine learning (ML) and natural language processing in the architectural engineering and construction sector to find which methodologies can assist this assessment. The paper carries out a systematic literature review, following the preferred reporting items for systematic reviews and meta-analyses guidelines, to survey the main scientific contributions within the topic of text classification (TC) for budgeting in construction. Findings This work concludes that it is necessary to develop data sets that represent the variety of tasks in construction, achieve higher accuracy algorithms, widen the scope of their application and reduce the need for expert validation of the results. Although full automation is not within reach in the short term, TC algorithms can provide helpful support tools. Originality/value Given the increasing interest in ML for construction and recent developments, the findings disclosed in this paper contribute to the body of knowledge, provide a more automated perspective on budgeting in construction and break ground for further implementation of text-based ML in budgeting for construction.

show abstract

Building Codes Part-of-Speech Tagging Performance Improvement by Error-Driven Transformational Rules

Xue

Zhang

2020

J. Comput. Civ. Eng.

View full text Add to dashboard Cite

Evaluation of Seven Part-of-Speech Taggers in Tagging Building Codes: Identifying the Best Performing Tagger and Common Sources of Errors

Cited by 3 publications

References 11 publications

Processamento de Linguagem Natural (PLN) para automatização da checagem de conformidade:

Processamento de Linguagem Natural (PLN) para automatização da checagem de conformidade:

Automation of text document classification in the budgeting phase of the Construction process: a Systematic Literature Review

Building Codes Part-of-Speech Tagging Performance Improvement by Error-Driven Transformational Rules

Contact Info

Product

Resources

About