Extracting Formal Models from Normative Texts
This work addresses the challenge of formalizing legal or regulatory documents for verification, but it is incremental as it builds on existing parsing techniques and requires manual post-editing.
The authors tackled the problem of analyzing normative texts by developing a semi-automatic tool that extracts formal models using dependency parsing and custom rules, reporting initial evaluations on accuracy and feasibility across multiple domains.
We are concerned with the analysis of normative texts - documents based on the deontic notions of obligation, permission, and prohibition. Our goal is to make queries about these notions and verify that a text satisfies certain properties concerning causality of actions and timing constraints. This requires taking the original text and building a representation (model) of it in a formal language, in our case the C-O Diagram formalism. We present an experimental, semi-automatic aid that helps to bridge the gap between a normative text in natural language and its C-O Diagram representation. Our approach consists of using dependency structures obtained from the state-of-the-art Stanford Parser, and applying our own rules and heuristics in order to extract the relevant components. The result is a tabular data structure where each sentence is split into suitable fields, which can then be converted into a C-O Diagram. The process is not fully automatic however, and some post-editing is generally required of the user. We apply our tool and perform experiments on documents from different domains, and report an initial evaluation of the accuracy and feasibility of our approach.