Challenges in technical regulatory text variation detection

From National Research Council Canada

Download	View final version: Challenges in technical regulatory text variation detection (PDF, 787 KiB)
Link	https://aclanthology.org/2025.regnlp-1.2/
Author	Search for: Chikati, Shriya Vaagdevi¹; Search for: Larkin, Samuel¹ORCID identifier: https://orcid.org/0009-0000-6147-9631; Search for: Minicola, David²; Search for: Lo, Chi-kiu¹ORCID identifier: https://orcid.org/0000-0001-8714-7846
Affiliation	National Research Council of Canada. Digital Technologies National Research Council of Canada. Construction
Format	Text, Article
Conference	1st Regulatory NLP Workshop, RegNLP 2025, Janurary 19 - 24, 2025, Abu Dhabi, United Arab Emirates
Abstract	We present a preliminary study on the feasibility of using current natural language processing techniques to detect variations between the construction codes of different jurisdictions. We formulate the task as a sentence alignment problem and evaluate various sentence representation models for their performance in this task. Our results show that task-specific trained embeddings perform marginally better than other models, but the overall accuracy remains a challenge. We also show that domain-specific fine-tuning hurts the task performance. The results highlight the challenges of developing NLP applications for technical regulatory texts.
Publication date	2025-01-20
Publisher	Association for Computational Linguistics
Licence	Creative Commons, Attribution 4.0 International (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/
In	Proceedings of the 1st Regulatory NLP Workshop, RegNLP 2025 (20 January 2025): 5–9.
Language	English
Peer reviewed	Yes
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	972b03b1-81fd-4c9e-b3e8-88e308eff012
Record created	2025-03-12
Record modified	2025-03-18

Date modified:: 2025-06-17