User-Guided Machine Understanding of Legal Documents

We present a novel approach to gaining a machine understanding of a legal document and then modelling the logic of that document in an integrated process. This paper describes a smart editor that uses a declarative language to represent both the ontology and logic models of a legal document. A document is incrementally elaborated in a fixed sequence of steps beginning with an ontology discovery step that identifies the explicit and implicit artefacts and applicable constraints. This information is used to generate code representations paired with words and icons which provide the foundation required for modelling the legal logic. The pairing with words and icons achieves a formal correspondence that allows logic modelling via either a textual or a graphical means. Similarly, this mechanism also supports both verbal and visual user feedback, enhancing user understanding. The tree of rules produced during this process is embedded in the original legal document, which can then be used as a smart contract on a modified blockchain. The integrated use of a declarative language auto-generated from a smart user interface for modelling both the ontology and the logic of a legal document, provides a simplicity and agility that enables domain experts to create and test custom smart contracts.