APPLICATION OF NATURAL LANGUAGE PROCESSING TECHNIQUES (NLP) IN URBAN CODE

Authors

  • Paulo Victor Matos Leite de Ávila Universidade Federal da Bahia
  • Douglas Malheiro de Brito Universidade Federal da Bahia
  • Daniele Mota Santos Universidade Federal da Bahia
  • Emerson de Andrade Marques Ferreira Universidade Federal da Bahia

DOI:

https://doi.org/10.4013/arq.2023.191.06

Keywords:

Natural Language Processing, Automation, Pre-processing, Artificial intelligence, Urban code

Abstract

Manually checking for compliance is a resource-intensive and error-prone task. Information in regulatory codes can be extracted automatically using natural language processing (NLP) techniques, making compliance checking simpler and more reliable. Although the PLN is an emerging area, there is still a relatively small amount of research applying to the Portuguese language. This study investigates a script using NLP techniques for the pre-processing – first phase of information extraction - of a Brazilian regulatory code. For this, the Python programming language and the NLTK library were used. An accuracy of 68% was achieved the performance of the labeller, indicating the need for improvements in the pre-processing for the Portuguese language. The main contribution of this study is to allow a greater understanding of the difficulties and probable causes of label errors in the pre-processing phase.

Downloads

Published

2024-04-08

How to Cite

Matos Leite de Ávila, P. V., Malheiro de Brito, D., Mota Santos, D., & de Andrade Marques Ferreira, E. (2024). APPLICATION OF NATURAL LANGUAGE PROCESSING TECHNIQUES (NLP) IN URBAN CODE. Arquitetura Revista, 19(1), 91–105. https://doi.org/10.4013/arq.2023.191.06

Issue

Vol. 19 No. 1 (2023): JAN-DEZ

Section

ENTAC 2022

License

I grant the journal Arquiteturarevista the first publication of my article, licensed under Creative Commons Attribution license (which allows sharing of work, recognition of authorship and initial publication in this journal).

I also take full responsibility for the copyright of images, photos and data included in the submitted work. I confirm that my article is not being submitted to another publication and has not been published in its entirely on another journal. I take full responsibility for its originality and I will also claim responsibility for charges from claims by third parties concerning the authorship of the article, its data and images.

I am responsible for approval in the specific ethics boards for each purpose, whenever necessary.