Estrella Project

Estrella Project

The European project for Standardized Transparent Representations in order to Extend Legal Accessibility (Estrella)

The Estrella project brought together a core group of researchers in the field of artificial intelligence and law (AI&Law). The ambition of the Estrella team was to provide an open standards based
solution covering all important constituents of a knowledge system. The project “foresaw
that such solution would require standards for documentary knowledge sources, a standard for describing (legal) knowledge, and a standard for the reasoning part. (The idea was to have) “the vendors participating in the project to take responsibility for the take up after the Project,…(the Estrella Project) not only created a reference operational environment that could guide these vendors in their future innovation process (Carneades), but (the Project) also made translators between the vendors current tools using the legal knowledge interchange format (LKIF). “(1)

The Estrella Project aimed “at developing and validating an open, standards-based platform
allowing public administrations to develop and deploy comprehensive legal knowledge
management solutions. The use of open-standard platforms allows users to be
independent from proprietary products of particular vendors; similarly they facilitate the development of different software solutions implementing such standards as well as guaranteeing scalability and interoperability among the applications, allowing public stakeholders to freely choose among competing development environments, inference engines, and other tools. (The Estrella Project supported)… both legal document management and legal knowledge systems, to provide a complete solution for improving the quality and efficiency of the determinative processes of public administration requiring the application of complex legislation and other legal sources.”(2)

The Project was set out to “address a significant barrier present in the market for Legal Knowledge Tools, such as rule-based systems such a barrier arising form the fact of there being different vendor formats for knowledge representation (e.g. rules expression), and there being no readily available standards, methods or tools for interchange of legal knowledge between vendor tolos.”(3)

The Project divided the work in work packages (WP1 to WP6). These WPs reflected the different issues to be covered.

Main Features

“Legal knowledge in (the Project) is represented by using a Legal Knowledge Interchange Format (LKIF), defined within the project as the main objective of WP1 (Workpackage 1). It is built upon emerging XML-based standards of the Semantic Web, including RDF and OWL, and Application Programmer Interfaces (APIs) for interacting with LKIF legal knowledge systems. … In order to establish explicit links between legal sources and legal knowledge, an open, general, jurisdiction independent and language independent XML based representation language able to describe legal sources will be defined as one of the main objectives of (Word Package 3). This standard for legal sources will be defined so that it can easily be used and coupled to LKIF knowledge models of these sources. Moreover, another primary objective of WP3 is represented by the specification and development of a Legal Sources Management System based on this standard format… This analysis is the background to further activities within the project, leading to the definition and management of a European XML standard for legal sources.”(4)

To achieve and demonstrate vendor neutrality and independence, translators between the LKIF format and the existing proprietary formats of LKBS vendors participating in the project will be developed.

Legal Knowledge Interchange Format (LKIF)

“The LKIF is built on but go beyond this generic work to allow further kinds of legal knowledge to be modelled, including: meta-level rules for reasoning about rule priorities and exceptions, legal arguments, legal procedures, cases and case factors, values and principles.”(5)

“LKIF is one of the important achievements of the Estrella project. In order to better connect the
legal knowledge models expressed in LKIF with the documentary knowledge sources expressed in CEN MetaLex, (the Estrella project) developed and additional standard called Legal Meta data Interchange Format (LMIF). Last but not least a fully Semantic Web compliant reasoning environment was developed which helped (the Project) to explore the strengths and weaknesses of the standard knowledge representation languages developed in the W3C consortium when applied in the legal domain. This environment called Harness was not foreseen at the beginning of the project and this achievement is complementary to the Carneades framework and could be integrated within that framework in the future.”(6)

The Legal Knowledge Interchange Format (LKIF) has been “build upon emerging XML-based standards of the Semantic Web, including RDF and OWL. LKIF extends the current W3C standards byincluding meta-level rules for reasoning about rule priorities and exceptions, legal arguments, legal procedures, cases and case factors, values and principles.”(7nuevo)

The members of the Project have successfully developed the LKIF and have supported LKIF with a “reference architecture and tools, as well as demonstrating LKIF in a series of realistic pilots hosted by key Governmental bodies forming part of the legal-draft and implementation process in their respective countries. LKIF is now available, and in fact has been adopted by vendors outside the project as a standard for legal knowledge interchange. We recognise that in order to further promote LKIF as a sustainable open standard additional activities should be started outside of the Estrella project. These activities will include a standardisation activity through a standardisation body, such as CEN.”(8)

The Estrella Project also created a “set of translators to and from the vendor’s proprietary formats to LKIF. The translators allow clients of the vendors in the consortium to port from one vendor’s solution to the other. It also allows them to share their formalised legal knowledge with other users and therefore creates a basis for better reuse of legal knowledge between different governmental users and between governments and businesses.”(9)

The Project developed an “OWL ontology of basic legal concepts (the LKIF-core ontology).
Besides being a modelling aid for knowledge engineers working in the legal domain, the LKIF-core ontology provides a basis for bridging between different legal cultures and languages. The LKIF-core ontology has been used to create LMIF and the different domain models that were used in the
knowledge systems developed for the user partners in the Estrella project.”(10)

Estrella Project main goals and outcome

“The primary business objective of the ESTRELLA project was to develop and validate an open, standards-based platform allowing public administrations to develop and deploy comprehensive legal knowledge management solutions, without becoming dependent on proprietary products of particular vendors.

(The Estrella Project) has provided support, in an integrated way, for both legal document
management and legal knowledge systems. The different solutions created provide a complete solution for improving the quality and efficiency of the determinative processes of public administration requiring the application of complex legislation and other legal sources. The solutions provided by (the Project) facilitate a market of interoperable components for legal knowledge
systems, allowing public administrations and other users to freely choose among competing development environments, inference engines, and other tools.”(11)

“The Estrella project has successfully completed the tasks set at the beginning. All deliverables that were foreseen have been delivered and the client partners have been provided with solutions for their problems stated at the first phase of the Project.”(12)

Reference inference engine for LKIF (Carneades)

“Carneades is an open source implementation of a hybrid architecture that supports legal reasoning including legal argumentation. This system is intended to serve as a demonstrator for LKIF and as a reference for the vendors when further developing their current tools.”(13)

eXistrella

This is a content management solution for handling pluriform textual (legal) knowledge sources (eXistrella).

“Exploiting the developed standard for describing legal sources MetaLex, an open source content management solution was created that enables users to manage huge amounts of legal documents and use these documents either directly via normal search and retrieval tools or via intelligent systems including legal knowledge systems. The eXistrella system also provides meta data support which improves precision and recall of document search and enables relating various sources using an advanced referential system. (The Estrella Project team) developed a Legal Meta data Interchange Format (LMIF) which can be viewed as a pre-proposal for a meta data standard. LMIF allows (the Estrella Project members) to relate formal legal knowledge modelled in LKIF with legal sources describe in MetaLex.”(14)

Harness

As a fully Semantic Web compliant knowledge architecture, Harness was “developed in order to test the strengths and weaknesses of a fully Semantic Web compliant solution for modelling and applying legal knowledge. Harness (allowed the Project) to create decidable knowledge components
which results can be trusted and that guarantee the complete exploration of a knowledge domain.(15) “Hybrid reasoning, i.e. combining a knowledge base that contained norms and a knowledge base that contained terminological knowledge (ontology) became probably attainable.”(16) “Due to
fundamental problems in aligning a DL (Description Logic) reasoner wit a rule engine, (the Project) arrived halfway with a solution that combines reasoning with an ontology and a normative knowledge
base, both expressed in OWL 2 DL.”(17)

Resources

Notes and References

  1. Estrella Project Presentation
  2. Estrella Deliverable: General XML format(s) for legal Sources
  3. Idem 1
  4. Idem 2
  5. Idem 2
  6. Estrella Project Presentation
  7. Idem
  8. Idem
  9. Idem
  10. Idem
  11. Idem
  12. Idem
  13. Idem
  14. Idem
  15. Idem
  16. Developing HARNESS.Towards a hybrid architecture for LKIF
  17. Idem

See Also

  • Semantic Web and Law
  • Semantic Indexing and Law
  • MetaLex
  • SDU BWB
  • LexDania
  • NormeinRete
  • AKOMA NTOSO
  • CHLexML
  • EnAct
  • Legal RDF
  • eLaw
  • LAMS
  • JSMS
  • UKMF
  • Legal Ontologies
  • Artificial Intelligence and Law
  • LegalXLM
  • CELEX
  • Linked Data Principles to Legal Information
  • Legal concepts
  • Legal Gateways Resources
  • International legal sources of information
  • Free Access to Law Movement
  • Legal Information Institute resources

Further Reading

  • Arnold-Moore, T. (1997). Automatic generation of amendment legislation. In Proceedings of the International Conference of Artificial Intelligence and Law.
  • Lachmayer, F. and Hoffmann, H. (2005). From legal categories towards legal ontologies. In Proceedings of the International Workshop on Legal Ontologies and Artificial Intelligence Techniques.
  • Doerr, M., Hunter, J., Lagoze, C., (2003) Towards a Core Ontology for Information
    Integration, in Journal of Digital Information, Volume 4 Issue 1, 2003
  • Fellbaum, C. (ed.) (1998). WordNet: An Electronic Lexical Database. MIT Press,
    Cambridge, Mass.

The Estrella project has resulted in many scientific publications. These include:

  • A. Boer, R. Winkels, and F. Vitali. MetaLex XML and the Legal Knowledge Interchange Format. Computable Models of the Law. Springer Verlag, Berlin, 2008.
  • Rinke Hoekstra. Use of owl in the legal domain (statement of interest). In Kendall Clark and Peter F. Patel-Schneider, editors, Proceedings of OWL: Experiences and Directions (OWLED 2008 DC), Washington, DC (metro), April 2008.
  • Szymon Klarman, Rinke Hoekstra, and Marc Bron. Versions and applicability of concept definitions in legal ontologies. In Kendall Clark and Peter F. Patel-Schneider, editors, Proceedings of OWL: Experiences and Directions (OWLED 2008 DC), Washington, DC (metro), April 2008.
  • E. de Maat, R. Winkels, and T. van Engers. Making Sense of Legal Texts. In G. Grewendorf and M. Rathert, editors, Formal Linguistics and Law, Trends in Linguistics – Studies and Monographs (TiLSM). Mouton, De Gruyter, Berlin, (in press) 2008.
  • Saskia van de Ven, Joost Breuker, Rinke Hoekstra, Lars Wortel, and Abdallah El-Ali. Automated legal assessment in OWL 2. In Legal Knowledge and Information Systems. Jurix 2008: The 21st Annual Conference, Frontiers in Artificial Intelligence and Applications. IOS Press, December 2008.
  • Saskia van de Ven, Rinke Hoekstra, Joost Breuker, Lars Wortel, and Abdallah El-Ali. Judging Amy: Automated legal assessment using OWL 2. In Proceedings of OWL: Experiences and Directions (OWLED 2008 EU), October 2008.
  • A. Wyner, T. Bench-Capon and K. Atkinson. Three Senses of `Argument’. To appear in Computable Models of the Law: Languages, Dialogues, Games, Ontologies. LNAI, volume 4884, 2008.
  • A. Wyner and T. Bench-Capon. Modelling Judicial Context in Argumentation Frameworks. To appear in COMMA 2008, Frontiers in Artificial Intelligence and Applications. IOS Press, 2008.
  • Alexander Boer, Radboud Winkels, and Fabio Vitali. Proposed XML standards for law: Metalex and LKIF. In Arno R. Lodder and Laurens Mommers, editors, Legal Knowledge and Information Systems. Jurix 2007: The Twentieth Annual Conference Annual Conference, volume 165 of Frontiers in Artificial Intelligence and Applications, pages 19-28. IOS Press, December 2007.
  • Emile de Maat and Radboud Winkels. Categorisation of norms. In Arno R. Lodder and Laurens Mommers, editors, Legal Knowledge and Information Systems. Jurix 2007: The Twentieth Annual Conference Annual Conference, volume 165 of Frontiers in Artificial Intelligence and Applications, pages 79-88. IOS Press, December 2007.
  • Gordon, T. F. Constructing arguments with a computational model of an argumentation scheme for legal rules. In Proceedings of the Eleventh International Conference on Artificial Intelligence and Law (2007).
  • Gordon, T. F. Visualizing Carneades argument graphs. Law, Probability and Risk; doi: 10.1093/lpr/mgm026.
  • Gordon, T. F., Prakken, H., and Walton, D. The Carneades model of argument and burden of proof. Artificial Intelligence 171, 10-11 (2007), 875-896.
  • Rinke Hoekstra, Joost Breuker, Marcello Di Bello, and Alexander Boer. The LKIF Core ontology of basic legal concepts. In Pompeu Casanovas, Maria Angela Biasiotti, Enrico Francesconi, and Maria Teresa Sagri, editors, Proceedings of the Workshop on Legal Ontologies and Artificial Intelligence Techniques (LOAIT 2007), June 2007.
  • Szymon Klarman and Marc Bron. Representing definitional changes in legal ontologies. In Xavier Binefa, Marie Francine Moens, José Manuel López-Cobo, and Pompeu Casanovas, editors, Proceedings of the Workshop on Multimedia Ontologies and Artificial Techniques 2007 (MOAIL-07), Leiden, December 2007.
  • A. Wyner and T. Bench-Capon. Towards an Extensible Argumentation System. In Proceedings of the European Conferences on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU 2007), volume 4724, pages 283-294. LNAI, 2007.
  • A. Wyner and T. Bench-Capon. Argument Schemes for Legal Case-based Reasoning. Jurix 2007: The Twentieth Annual Conference Annual Conference, volume 165 of Frontiers in Artificial Intelligence and Applications, pages 139-149. IOS Press, December 2007.
  • A. Wyner, T. Bench-Capon and K. Atkinson. Arguments, Values and Baseballs: Representation of Popov v. Hayashi. Jurix 2007: The Twentieth Annual Conference Annual Conference, volume 165 of Frontiers in Artificial Intelligence and Applications, pages 151-160. IOS Press, December 2007.
  • Gordon, T. F., and Walton, D. Pierson vs. Post revisted – a reconstruction using the Carneades Argumentation Framework. In Proceedings of the First International Conference on Computational Models of Argument (COMMA 06) (Liverpool, 2006), P. E. Dunne and T. Bench-Capon, Eds., IOS Press.
  • Gordon, T. F., and Walton, D. The Carneades argumentation framework – using presumptions and exceptions to model critical questions. In Proceedings of the First International Conference on Computational Models of Argument (COMMA 06) (Liverpool, September 2006), P. E. Dunne, Ed.
  • Joost Breuker, Alexander Boer, Rinke Hoekstra, and Kasper van den Berg. Developing content for LKIF: Ontologies and frameworks for legal reasoning. In Tom M. van Engers, editor, Legal Knowledge and Information Systems. Jurix 2006: The Nineteenth Annual Conference, volume 152 of Frontiers in Artificial Intelligence and Applications, pages 169-174. IOS Press, December 2006.

Posted

in

, ,

by

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *