Similarity analysis on government regulations

Abstract

Government regulations are semi-structured text documents that are often voluminous, heavily cross-referenced between provisions and even ambiguous. Multiple sources of regulations, like those from federal, state, and local offices, lead to difficulties in both understanding and complying with all applicable codes. In this work, we propose a framework for regulation management and similarity analysis. An online repository for legal documents is created with the help of text mining tool, and users can access regulatory documents either through the natural hierarchy of provisions or from a taxonomy based on concepts generated by knowledge engineers. Our similarity analysis core identifies relevant provisions and brings them to the user's attention, and this is performed by utilizing both the structure and referencing of regulations to provide a better comparison between provisions. Preliminary results show that our system reveals hidden similarities between provisions that are not identified using traditional comparison techniques.

Addressing Legal Requirements in Requirements Engineering

“…Such supplemental references may include previous administrative rulings, reference handbooks, or other published guides to interpreting the regulation [24]. The ambiguity associated with regulations has forced government agencies to provide these detailed reference materials and instructive handbooks to aid understanding and compliance efforts [28]. For example, the U.S. Department of Health and Human Services publishes a summary of the Health Insurance Portability and Accountability Act (HIPAA) 1 Privacy Rule and guidance documents for implementing the HIPAA Security Rule.…”

“…In addition, some newer legal texts are already being represented in XML; augmenting these existing representations is a relatively easy task [35]. Research efforts in this area include: SGML modeling of decisions of the Supreme Court of Canada [40]; REGNET, an XML framework for representing regulations [24,25,28,29,30]; and an overview of several XML models for representing legal texts [35].…”

Assessing regulatory change through legal requirements coverage modeling

“…Regulations are interconnected, and Maxwell et al describe a taxonomy for understanding the impact of legal cross references on requirements [18]. In comparing multiple laws, Lau et al conducted a similarity analysis of regulations to identify related regulatory texts [16] and Gordon and Breaux proposed requirements "water marking" as an analysis method to identify high and low standards of care across multiple regulations [13]; this method is based on previously validated gap analysis metrics [6]. With regards to assessing proposed laws, Maxwell et al studied proposed changes to the HIPAA regulations to identify areas of law that were subject to change [19], which may affect requirements changes in our framework.…”

Legal information retrieval and application to e-rulemaking

“…If we take the ADAAG and the UFAS as an example, they generate just over a thousand concepts together. For other features such as measurements and dates, handcrafted rules are implemented to automatically match them in provisions [30]. The corpus of documents is refined with the extracted features tagged as additional XML elements in provisions where they appear.…”