Dr. Adam Wyner of the University of Liverpool Department of Computer Science, and Dr. Wim Peters of the University of Sheffield Department of Computer Science, have posted their paper entitled On Rule Extraction from Regulations, to be presented at JURIX 2011: The 24th International Conference on Legal Knowledge and Information Systems, 14-16 December 2011, in Vienna, Austria.
Here is the abstract:
Rules in regulations such as found in the US Federal Code of Regulations can be expressed using conditional and deontic rules. Identifying and extracting such rules from the language of the source material would be useful for automating rulebook management and translating into an executable logic. The paper presents a linguistically-oriented, rule-based approach, which is in contrast to a machine learning approach. It outlines use cases, discusses the source materials, reviews the methodology, then provides initial results and future steps.
The empirical component of the study involves application of the method and model to text from 21 Code of Federal Regulations part 610, section 40 (21 C.F.R. 610.40).