Prof. Kevin D. Ashley - Scuola di Giurisprudenza
FSCUOLA ACOLTÀ DI GIURISPRUDENZA ALMA MATER STUDIORUM – UNIVERSITÀ DI BOLOGNA SEMINARIO DI INFORMATICA GIURIDICA CATTEDRADELLA DELLA PROMOSSO DALLA CATTEDA PROF.SSA MONICA PALMIRANI A.A. 2014/2015 VIA ZAMBONI 22, AULA 4 RESEARCH PROGRESS IN ARTIFICIAL INTELLIGENCE AND LAW: AN INTELLECTUAL SURVEY Prof. Kevin D. Ashley URL: http://www.lrdc.pitt.edu/ashley/Kevin%20Ashley%27s%20Home%20Page.html Email: [email protected] Professor of Law and Intelligent Systems University of Pittsburgh School of Law Senior Scientist, Learning Research and Development Center The course will comprise four three-hour seminar sessions. Session 1. Introduction to Computational Models of Legal Reasoning: Lessons Learned about Legal Rules and Cases. Provides an introduction to computational models of reasoning with legal rules or cases and explains some lessons AI and Law researchers have learned about each type of reasoning that should be of significance to law students. Session 2. Defeasible Legal Reasoning with Argument Schemes: Lessons Learned about Legal Argument. Addresses how recent advances in argumentation theory, argument schema and critical questions, and diagrammatic argument representations, impact ways in which researchers computationally model legal argument and the interpretation of legal norms, and design, implement, and evaluate legal expert systems. Session 3. Legal Information Retrieval, Information Extraction, and Text Processing: Lessons Learned about Legal Digital Documents Technologies. Surveys the state of the art in legal information retrieval and information extraction from texts, including from comparatively wellstructured texts such as legal statutes, regulations, and case opinions versus comparatively unstructured texts as in e-Discovery, which involves retrieving, often from enormous databases of digital information, all documents that may be relevant to legal issues in particular litigation contexts. Session 4. The Future of AI and Law: Bridging Computational Models and Legal Texts. Discusses prospects and techniques for enabling computational models of legal reasoning to work directly and automatically with legal texts. Introduction to AI & Law: Artificial Intelligence and Law is a subfield of AI research that focuses on computationally modeling legal reasoning for the purpose of building tools to assist in legal practice and pedagogy and of studying legal reasoning in order to contribute to cognitive science and jurisprudence. From the viewpoint of cognitive science and AI, legal reasoning is especially interesting because it falls somewhere between the comparatively well-structured domains of mathematical and scientific reasoning for which AI researchers have developed useful methodologies and the comparatively unstructured common sense domains of ordinary discourse that AI researchers someday hope to model. From a jurisprudential viewpoint, AI and Law offers the promise of embodying theories in a computational form that can be applied systematically to a range of examples; as the theories fail on the margins, the computational models can be improved in an effort to make scientific progress in studying law. Course Materials: Readings will be distributed electronically via a TWEN course website at lawschool.westlaw.com. In order to access the site, students will need to use a Westlaw password and a course password, which the instructor will distribute via email. Readings marked with an asterisk [*] below are highly recommended. Unmarked readings are required. Course requirement: In order to stimulate classroom discussion and foster understanding of the readings, for each session, each student should prepare a one-page critique for at least one reading marked [*]. These one-page critiques should be submitted electronically to the instructor the day before each seminar session. The critiques should comprise four parts: (a) a brief statement of what the paper is about, and short descriptions of: (b) the strengths of the approach, (c) the weaknesses of the approach, and (d) the relevance of the paper to some project, paper, or topic of interest to the student. Please send an email to [email protected] to facilitate organizing the lectures. PROGRAMME Session 1 1st December 14:0017:00 Aula 4 Session 2 2nd December 14:0017:00 Aula 4 Session 3 3rd December 14:0017:00 Aula 4 Session 4 4th December 14:0017:00 Aula 4 Introduction to Computational Models of Legal Reasoning: Lessons Learned about Legal Rules and Cases Readings to be discussed: • Pages 783-795; 802- 817Ashley, K. (2013) “Teaching Law and Digital Age Legal Practice with an AI and Law Seminar.” Chicago Kent Law Review. 88:3: 783-844 (2013). • [*] Vincent Aleven (2003) “Using Background Knowledge in Case-Based Legal Reasoning: A Computational Model and an Intelligent Learning Environment”. 150 Artificial Intelligence 183-238. • [*] L. Karl Branting (1991) "Building Explanations from Rules and Structured Cases". International Journal of Man-Machine Studies, 34(6):797--837. • [*] K. D. Ashley and S. Brüninghaus (2006) “Computer Models for Legal Prediction.” Jurimetrics Journal Vol. 46, pp. 309-352. • [*] Trevor Bench-Capon and Giovanni Sartor (2003) “A Model of Legal Reasoning with Cases Incorporating Theories and Values”. 150 Artificial Intelligence 97-143. Defeasible Legal Reasoning with Argument Schemes: Lessons Learned about Legal Argument Readings to be discussed: • Pages 796-797; 817-824 Ashley, K. (2013) “Teaching Law and Digital Age Legal Practice with an AI and Law Seminar.” Chicago Kent Law Review. 88:3: 783-844 (2013). • [*] Gordon, T. F., and Walton, D. (2009) Legal reasoning with argumentation schemes. Proc. 12th Int’l Conf. Artificial Intelligence and Law ICAIL 2009. • [*] Atkinson, K. and Bench-Capon, T. (2007): Argumentation and standards of proof. In Proc. 11th Int’l Conf. Artificial Intelligence and Law ICAIL 2007. 107-116. ACM Press. • [*] Grabmair, M. and Ashley, K.D. (2011) “Facilitating Case Comparison Using Value Judgments and Intermediate Legal Concepts.” Proceedings Thirteenth International Conference on Artificial Intelligence and Law (ICAIL 2011), pp. 161-170. ACM Press. Legal Information Retrieval, Information Extraction, and Text Processing: Lessons Learned about Legal Digital Documents Technologies Readings to be discussed: • Pages 797-799; 824-839 Ashley, K. (2013) “Teaching Law and Digital Age Legal Practice with an AI and Law Seminar.” Chicago Kent Law Review. 88:3: 783-844 (2013) • [*] Francesconi, E., Montemagni, S., Peters,W., and Tiscornia, D. (2010) Integrating a Bottom-Up and TopDown Methodology for Building Semantic Resources for the Multilingual Legal Domain. In Semantic Processing of Legal Texts. LNAI 6036, pp. 95-121. Springer: Berlin. • [*] Saravanan, M., B. Ravindran, and S. Raman (2009) Improving Legal Information Retrieval Using an Ontological Framework, Artificial Intelligence and Law, 17: 101-124. • [*] Daniels, J.J. and Rissland, E.L.(1997) Finding Legally Relevant Passages in Case Opinions. In Proceedings of the Sixth International Conference on Artificial Intelligence and Law. ICAIL-97 pp. 39-46. Association for Computing Machinery. New York. • [*] Khalid Al-Kofahi, Alex Tyrrell, Arun Vacher, and Peter Jackson, (2001). “A Machine Learning Approach to Prior Case Retrieval.” ICAIL-2001 88-93. The Future of AI and Law: Bridging Computational Models and Legal Texts Readings to be discussed: • Pages 799-800; Ashley, K. (2013) “Teaching Law and Digital Age Legal Practice with an AI and Law Seminar.” Chicago Kent Law Review. 88:3: 783-844 (2013). • [*] Brüninghaus, S. and Ashley, K.D. (2005). “Reasoning with Textual Cases,” in Proceedings, Fourth International Conference on Case-Based Reasoning ICCBR-05) pp. 137-151. • [*] Ashley, K. and Walker, V. (2013) From Information Retrieval (IR) to Argument Retrieval (AR) for Legal Cases: Report on a Baseline Study. Legal Knowledge and Information Systems. Jurix 2013: The Twenty-Sixth Annual Conference. p. 29 • Ashley, K. and Bridewell, W. (2010) Emerging AI & Law approaches to automating analysis and retrieval of electronically stored information in discovery proceedings. Artificial Intelligence and Law 18:311-320. • [*] Henseler, H. (2010) Network-based filtering for large email collections in E-Discovery. Artificial Intelligence and Law 18:413-430.