Analyzing government regulations using structural and domain information

Government regulations, by extending laws with specific guidance for corporate and public actions, provide an important societal benefit. Ideally, they should be intelligible to ordinary citizens as well as rule makers, but the volume of regulations coupled with heavy referencing between provisions limit their accessibility. Apart from the difficulties in locating and understanding a particular regulation, users often must consult and reconcile multiple authoritative sources. For example, US companies frequently must comply with overlapping federal, state, and local regulations; in addition, some nonprofit organizations publish their own codes of practice. The problem is exacerbated in the European Union, where regulators must harmonize legislation across countries with different languages and traditions. To address the difficulties encountered in comparing regulatory documents with multiple authoritative sources, the Regnet project is developing a relatedness analysis system that exploits such document´s unique computational properties.