What can we do when faced with many documents, often while trying to explore or make new documents related to existing ones? It is especially significant in the legislative process. Cross referencing various yet-to-be-published documents and bills/laws is one solution; this is what the authors explore in this research. They focus on automation using the xlinkit rule language as an essential tool for generating fine-grained cross-reference links of relevant legal texts. As the authors note, legal compliance is a concern for many software applications in domains including government, healthcare, and finance. In the process of identifying compliance requirements, system developers should review many relevant legal texts where “relationships between ... provisions in legal texts are captured using cross references.” It is interesting how, just like in their previous works, the authors emphasize natural language issues and Extensible Markup Language (XML) taxonomy importance in automated cross-reference resolution.
The authors are mainly focused on automatic detection and resolution of cross references in legal texts published online in structural and/or nonstructural ways. The authors’ approach is parameterized by a text schema, allowing the automated connection of non-markup legal texts with the structural markup that is necessary for resolving cross references. According to the paper’s abstract:
Enabling easier navigation and handling of cross references requires automated support for the detection of the natural language expressions used in cross references, the interpretation of cross references in their context, and the linkage of cross references to the targeted provisions.
These issues are evaluated through an automated framework for detecting and resolving cross references in Luxembourg’s legislation. Further, the results from the authors’ previous research are additionally validated in this study against the Canadian Personal Health Information Protection Act in order to further test the usability of the framework developed. It should be noted how hard work is needed when system developers must meet compliance requirements in the privacy and security field, the most demanding area of regulations compliance. That is why this work is a really valuable contribution to the literature on cross reference and reference resolution in the legal domain, as well as on unified automated processing of markup and nonformatted documents.