Aucher, Boella, & van der Torre on Privacy Policies with Modal Logic: The Dynamic Turn

Dr. Guillaume Aucher of the University of Luxembourg Faculty of Sciences, Technology and Communication, Professor Dr. Guido Boella of Università degli Studi di Torino Dipartimento di Informatica , and Professor Dr. Leon van der Torre of the University of Luxembourg Faculty of Sciences, Technology and Communication, have published Privacy Policies with Modal Logic: The Dynamic Turn, in DEON 2010: Proceedings of the 10th International Conference on Deontic Logic in Computer Science, 7-9 July 2010, Fiesole, Italy 196-213 (Guido Governatori & Giovanni Sartor eds., 2010). Here is the abstract:

Privacy policies are often defined in terms of permitted messages. Instead, in this paper we derive dynamically the permitted messages from static privacy policies defined in terms of permitted and obligatory knowledge. With this new approach, we do not have to specify the permissions and prohibitions of all message combinations explicitly. To specify and reason about such privacy policies, we extend a multi-modal logic introduced by Cuppens and Demolombe with update operators modeling the dynamics of both knowledge and privacy policies. We show also how to determine the obligatory messages, how to express epistemic norms, and how to check whether a situation is compliant with respect to a privacy policy. We axiomatize and prove the decidability of our logic.

Gonçalves & Quaresma on Multilingual Text Classification Through Combination of Monolingual Classifiers

Teresa Gonçalves and Professor Paulo Quaresma, both of Universidade de Évora Departamento de Informática, have published Multilingual Text Classification Through Combination of Monolingual Classifiers, in LOAIT 2010: Proceedings of the 4th Workshop on Legal Ontologies and Artificial Intelligence Techniques, European University Institute, Fiesole, Florence, Italy, July 7th, 2010, at 29-38 (Enrico Francesconi, Simonetta Montemagni, Piercarlo Rossi, and Daniela Tiscornia eds., 2010). Here is the abstract:

With the globalization trend there is a big amount of documents written in different languages. If these polylingual documents are already organized into existing categories one can deliver a learning model to classify newly arrived polylingual documents. Despite being able to adopt a simple approach by considering the problem as multiple independent monolingual text classification problems, this approach fails to use the opportunity offered by polylingual training documents to improve the effectiveness of the classifier. This paper proposes a method to combine different monolingual classifiers in order to get a new classifier as good as the best monolingual one having also the ability to deliver the best performance measures possible (precision, recall and F1). The proposed methodology was applied to a corpus of legal documents – from the EUR-Lex site – and was evaluated. The obtained results were quite good, indicating that combining different mono-lingual classifiers may be a promising approach to reach the best performance for each category independently of the language.

De Maat & Winkels on Suggesting Model Fragments for Sentences in Dutch Law

Emile de Maat and Professor Dr. Radboud Winkels, both of The Leibniz Center for Law of the University of Amsterdam, have published Suggesting Model Fragments for Sentences in Dutch Law , in LOAIT 2010: Proceedings of the 4th Workshop on Legal Ontologies and Artificial Intelligence Techniques, European University Institute, Fiesole, Florence, Italy, July 7th, 2010, at 19-28 (Enrico Francesconi, Simonetta Montemagni, Piercarlo Rossi, and Daniela Tiscornia eds., 2010). Here is the abstract:

A main issue in the field of artificial intelligence and law is the translation of source of law that are written in natural language into formal models of law. This article describes a step in that transformation: the creation of models for individual sentences in a source of law. The approach uses a natural language parse to analyse the sentence, and then translates the resulting parse tree to a formal model, using both generic and law-specific attributes.

Wyner, Towards Annotating and Extracting Textual Legal Case Elements

Dr. Adam Wyner of the University of Leeds Centre for Digital Citizenship has published Towards Annotating and Extracting Textual Legal Case Elements, in LOAIT 2010: Proceedings of the 4th Workshop on Legal Ontologies and Artificial Intelligence Techniques, European University Institute, Fiesole, Florence, Italy, July 7th, 2010, at 9-18 (Enrico Francesconi, Simonetta Montemagni, Piercarlo Rossi, and Daniela Tiscornia eds., 2010). Here is the abstract:

In common law contexts, legal cases are decided with respect to precedents rather than legislation as in civil law contexts. Legal professionals must find, analyse, and reason with and about cases drawn from a set of cases (a case base). A range of particular textual elements of a case may be relevant to query and extract. Commercial providers of legal information allow legal professionals to search a case base by keywords and meta data. However, the case base and the search tools are proprietary, of limited, non-extensible functionality, and are restricted access. Moreover, no provider applies natural language processing techniques to the cases for text analysis, XML annotation, or information acquisition. In this paper, we discuss an initial experiment in developing and applying natural language processing tools to cases to produce annotated text which can then support information extraction.

Stede & Kuhn on Identifying the Content Zones of German Court Decisions

Professor Dr. Manfred Stede and Florian Kuhn, both of Universität Potsdam Department Linguistik, have published Identifying the Content Zones of German Court Decisions, in Business Information Systems Workshops: BIS 2009 International Workshops, Poznan, Poland, April 27-29, 2009, Revised Papers (2009).

The paper was originally presented at LIT 2009: The 2nd Workshop on Legal Informatics and Legal Information Technology, held 28 April 2009 in Poznan, Poland.

Here is the abstract of the paper:

A central step in the automatic processing of court decisions is the identification of the various content zones, i.e., breaking up the document into functionally independent areas. We assembled a corpus of German court decisions and argue that this genre belongs to the class of semi-structured text documents. Currently, we are implementing zone identification by means of a set of recognition rules, following up on our earlier experiences with a different genre (film reviews).

Wyner on Onto Root Gazetteer

Dr. Adam Wyner of the University College London Department of Computer Science has posted detailed notes on Onto Root Gazetteer (ORG), a plugin for GATE, the General Architecture for Text Engineering. This post may be of interest to researchers or developers using GATE for automatic text processing of legal documents.

Dr Wyner explains that “ORG annotates [a] text with respect to [a designated] ontology.” In his post, Dr. Wyner “present[s] User Manual notes for ORG, references to ORG, and some discussion.”

Cornell Digital Law Library Meeting

During the week of October 13, 2009, a very rewarding informal meeting of digital law library developers, administrators, and researchers took place at Cornell University’s Legal Information Institute. The gathering was graciously hosted by Dr. Tom Bruce. The purpose of the meeting was to discuss a number of issues respecting free access to law, legal information institutes, and digital law libraries. Photos of the meeting are available here and here. Among the participants were:

• Professor Daniel Poulin, Director of CANLII & LexUM Laboratory;
• Marc-André Morissette, Chief Analyst at LexUM Laboratory;
• Pierre-Paul Lemyre, Head of Products and Business Development at LexUM Laboratory and a Ph.D. student at University of Montreal Faculté de Droit, studying the effects on legal systems of free access to law & legal information institutes;
• Daniel Shane, Software Developer at LexUM Laboratory;
• Elmer Masters, Director of Internet Development at CALI;
• John Joergensen, Reference & Circulation Librarian at the Rutgers University Camden Law Library, and developer of the Rutgers University Camden Law Library Digital Collections;
• Stuart Sierra, Assistant Director of the Program on Law & Technology at Columbia Law School and developer of AltLaw: The Free Legal Search Engine; and
• Sara Frug, Brian Hughes, Daniel Nagy, & David Shetland of Cornell’s Legal Information Institute.

On October 14-15, the following topics were discussed:

• Professor Poulin, Marc-André Morissette, Pierre-Paul Lemyre, & Daniel Shane discussed information acquisitions, text-processing methods, the treatment of images in court decisions, and administrative matters, respecting CANLII;
• Dr. Bruce, Daniel Nagy, & Sara Frug of Cornell’s LII, & Elmer Masters of CALI discussed their use of Drupal to present a variety of types of content, their text processing methods, and the costs and benefits of cloud computing;
• Dr. Bruce, Daniel Nagy, Elmer Masters, and Tim Stanley & Nicolas Moline of Justia discussed using OpenID & OAuth to enable streamlined authentication & access to online legal resources;
• Dr. Bruce, Professor Poulin, and others discussed various methods of legal metadata standardization, including encouraging courts, legislatures, and administrative agencies to adopt publishing standards, and the development and promotion of OAI4Courts as a means of standardizing metadata for court documents, to enable sharing and aggregation of such metadata in open repositories;
• Stuart Sierra described his methods for automated acquisition of US Federal Court decisions, as well as his text processing and data management techniques at AltLaw;
• John Joergensen described his methods for automated acquisition of court decisions, text processing, procedures for digitizing print and microfiche legal documents, and digital preservation techniques, at the Rutgers University Camden Law Library’s digital collections.

On October 16, the following topics were discussed:

• Prof. Poulin discussed the former challenges of adding secondary sources to CANLII, the new possibilities of adding commentary and user generated content to CANLII, and his desire that CANLII be a generative system, in Professor Jonathan Zittrain’s sense of that term in The Future of the Internet and How to Stop It;
• Dr. Bruce, Prof. Poulin, Elmer Masters, and all the participants discussed their plans for sustaining innovation in the coming years at LII, CANLII, & CALI, and for developing business models and strategies;
• Dr. Bruce emphasized the need to develop standards to enable sharing of metadata and legal information objects among digital repositories, and to educate reporters of decisions about the need to enable information sharing in legal digital publishing;
• The LexUM team discussed two different approaches to taxonomies that they have tested respecting CANLII;
• Pierre-Paul Lemyre demonstrated several LexUM Web 2.0 projects, including Le Code civil du Quebéc annoté, which allows users to add annotations, and the CANLEX set of APIs for CANLII, including the RefLex API, which hotlinks legal citations in a user’s document. Prof. Poulin & Pierre-Paul also discussed Lexacto, a search engine enabling practitioners to index and retrieve content on particular legal topics, whether that content is located within or outside their firm. Some of this new technology will be tested at the Supreme Court of Canada;
• Marc-André Morissette demonstrated a drop-down table of contents-based document management system for legislative materials, called LexView, with the Canadian Criminal Code as a prototype. He said that similar technology would be applied to the Nova Scotia Annotated Civil Procedure Rules and continuing legal education materials for British Columbia;
• Dr. Bruce, Elmer Masters, John Joergensen, and the Cornell LII team discussed implementation of OpenID, the possible sharing of taxonomies, and possible collaboration respecting data for updating the U.S. Code;
• In a wrap-up discussion, each participant identified the most valuable information they acquired during the meeting. John Joergensen initiated a new discussion about the need for the legal information institutes to consider new issues in light of the institutes’ maturation and acceptance as key actors in the legal information infrastructure, and underscored digital preservation as one such issue. Dr. Bruce & Prof. Poulin reflected on their careers leading legal information institutes and how their personal roles had changed as their organizations had grown and matured.
• The participants agreed to meet again next autumn, either in Ithaca or in Montreal. Everyone thanked Dr. Bruce and the Cornell LII team for their gracious hospitality.

Many thanks to Dr. Bruce & his team for their gracious hospitality and stimulating discussion.