Ishini Saparamadu

Ms. Ishini Saparamadu

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 March 2025 in Buildings
Verified
Journal Article
Open access
PDF file
ISIshini Saparamadu
Ishini Saparamadu
Samad SepasgozarSamad Sepasgozar
Samad Sepasgozar
RGRomasha Nethmini Deveni Guruge
Romasha Nethmini Deveni Guruge
HJH. S. Jayasena
H. S. Jayasena
Ali DarejehAli Darejeh
Ali Darejeh
Balachandra Arachchige Isuru ErangaBalachandra Arachchige Isuru Eranga
Balachandra Arachchige Isuru Eranga
Frequent ambiguities in contract terms often lead to costly legal disputes and project delays in the construction industry. Large Language Models (LLMs) offer a promising solution, enhancing accuracy and reducing misinterpretations. As studies pointed out, many professionals use LLMs, such as ChatGPT, to assist with their professional tasks at a minor level, such as information retrieval from the Internet and content editing. With access to a construction regulation database, LLMs can automate contract interpretation. However, the lack of Artificial Intelligence tools tailored to industry regulations hinders their adoption in the construction sector. This research addresses the gap by developing and deploying a publicly available specialised chatbot using the ChatGPT language model. The development process includes architectural design, data preparation, vector embeddings, and model integration. The study uses qualitative and quantitative methodologies to evaluate the chatbot’s role in resolving contract-related issues through standardised tests. The specialised chatbot, trained on construction-specific legal information, achieved an average score of 88%, significantly outperforming ChatGPT’s 36%. The integration of a domain-specific language model promises to revolutionise construction practices through increased precision, efficiency, and innovation. These findings demonstrate the potential of optimised language models to transform construction practices.

1 August 2024
Verified
Conference Paper
Closed access
PDF file
ISIshini Saparamadu
Ishini Saparamadu
HJH.S. Jayasena
H.S. Jayasena
Balachandra Arachchige Isuru ErangaBalachandra Arachchige Isuru Eranga
Balachandra Arachchige Isuru Eranga
The recent exponential advancements in Natural Language Processing (NLP) are catalysing a paradigm shift in the world, directing the construction industry towards an era of smart construction. The proficiency of NLP in comprehending and assimilating vast quantities of human language data aligns aptly with the construction sector’s exigency for enhanced management of its unstructured textual data. Given the frequent alterations in regulatory frameworks and the dispersed nature of project data, there arises a compelling need for a Natural Language Processing Powered Compliance Management Nexus (NLP-PCMN), which facilitates expedited access to consolidated information via mobile platforms. This study aims to develop a blueprint for implementing an NLP-PCMN in the construction industry. By conducting semi-structured interviews with 20 experts spanning the domains of construction and Artificial Intelligence (AI) alongside a focus group to outline the technological framework of the NLP-PCMN, the research underscores the need to implement such a system. The envisaged system is poised to address challenges such as navigating contract clauses, correspondence analysis and ensuring legal compliance with planning and building codes and legal provisions. The proposed NLP-PCMN presents a comprehensive solution integrating these features through large language models that work as a question-and-answering system. Key findings include the necessity of automating the regulatory and legal data in construction, stakeholder empowerment through NLP-PCMN, identifying the nodes of the NLP-PCMN and the technical blueprint to implement the NLP-PCMN.