Comparison and Synergy Between Fact-Orientation and Relation Extraction for Domain Model Generation in Regulatory Compliance

Modern enterprises need to treat regulatory compliance in a holistic and maximally automated manner, given the stakes and complexity involved. The ability to derive the models of regulations in a given domain from natural language texts is vital in such a treatment. Existing approaches automate regulatory rule extraction with a restricted use of domain models counting on the knowledge and efforts of domain experts. We present a semi-automated treatment of regulatory texts by automating in unison, the key steps in fact-orientation and relation extraction. In addition, we utilize the domain models in learning to identify rules from the text. The key benefit of our approach is that it can be applied to any legal text with a considerably reduced burden on domain experts. Early results are encouraging and pave the way for further explorations.

[1]  Edgar R. Weippl,et al.  IT Governance, Risk & Compliance (GRC) Status Quo and Integration: An Explorative Industry Case Study , 2011, 2011 IEEE World Congress on Services.

[2]  Sergey Brin,et al.  Extracting Patterns and Relations from the World Wide Web , 1998, WebDB.

[3]  Jun'ichi Tsujii,et al.  Boosting Precision and Recall of Dictionary-Based Protein Name Recognition , 2003, BioNLP@ACL.

[4]  Tom M. van Engers,et al.  A Case Study on Automated Norm Extraction , 2004 .

[5]  Radboud Winkels,et al.  Automatic Classification of Sentences in Dutch Laws , 2008, JURIX.

[6]  Huang Xun,et al.  A Review of Relation Extraction , 2013 .

[7]  Fredrik Olsson,et al.  A literature survey of active machine learning in the context of natural language processing , 2009 .

[8]  Terry A. Halpin,et al.  The NORMA Software Tool for ORM 2 , 2010, CAiSE Forum.

[9]  Luigi Logrippo,et al.  Governance Requirements Extraction Model for Legal Compliance Validation , 2009, 2009 Second International Workshop on Requirements Engineering and Law.

[10]  Oren Etzioni,et al.  Identifying Relations for Open Information Extraction , 2011, EMNLP.

[11]  Zellig S. Harris,et al.  Mathematical structures of language , 1968, Interscience tracts in pure and applied mathematics.

[12]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[13]  Claudia Soria,et al.  Automatic semantics extraction in law documents , 2005, ICAIL '05.

[14]  Wim Peters,et al.  On Rule Extraction from Regulations , 2011, JURIX.

[15]  Terry A. Halpin,et al.  Fact-Orientation and Conceptual Logic , 2011, 2011 IEEE 15th International Enterprise Distributed Object Computing Conference.

[16]  Vinay Kulkarni,et al.  Explanation of Proofs of Regulatory (Non-)Compliance Using Semantic Vocabularies , 2015, RuleML.

[17]  Oren Etzioni,et al.  Open Language Learning for Information Extraction , 2012, EMNLP.

[18]  John Mylopoulos,et al.  GaiusT: supporting the extraction of rights and obligations for regulatory compliance , 2013, Requirements Engineering.

[19]  Marie-Francine Moens,et al.  Automatic detection of arguments in legal texts , 2007, ICAIL.

[20]  Annie I. Antón,et al.  Deriving semantic models from privacy policies , 2005, Sixth IEEE International Workshop on Policies for Distributed Systems and Networks (POLICY'05).

[21]  Radboud Winkels,et al.  Machine Learning versus Knowledge Based Classification of Legal Texts , 2010, JURIX.

[22]  John Mylopoulos,et al.  Automating the Extraction of Rights and Obligations for Regulatory Compliance , 2008, ER.

[23]  Terry A. Halpin,et al.  Enhanced Verbalization of ORM Models , 2012, OTM Workshops.