A relatedness analysis of government regulations using domain knowledge and structural organization

The complexity and diversity of government regulations make understanding and retrieval of regulations a non-trivial task. One of the issues is the existence of multiple sources of regulations and interpretive guides with differences in format, terminology and context. This paper describes a comparative analysis scheme developed to help retrieval of related provisions from different regulatory documents. Specifically, the goal is to identify the most strongly related provisions between regulations. The relatedness analysis makes use of not only traditional term match but also a combination of feature matches, and not only content comparison but also structural analysis.Regulations are first compared based on conceptual information as well as domain knowledge through feature matching. Regulations also possess specific organizational structures, such as a tree hierarchy of provisions and heavy referencing between provisions. These structures represent useful information in locating related provisions, and are therefore exploited in the comparison of regulations for completeness. System performance is evaluated by comparing a similarity ranking produced by users with the machine-predicted ranking. Ranking produced by the relatedness analysis system shows a reduction in error compared to that of Latent Semantic Indexing. Various pairs of regulations are compared and the results are analyzed along with observations based on different feature usages. An example of an e-rulemaking scenario is shown to demonstrate capabilities and limitations of the prototype relatedness analysis system.

Gio WiederholdEmail: