An Agent-Based Intelligent Tutoring System: A Case Study in Legal Domain

Federal University of Alagoas - Campus ArapiracaCampo da Sementeira - AL 115, KM 3 S/N Arapiraca - ALEmail: romulo@dsc.ufcg.edu.brAbstract: Computer based learning gets more and more im-portant in higher education. Particularly, in Legal domain, stu-dents have little chance to deal with realistic situations. Oneway to alleviate this problem is to provide Law students withreal cases, rules, and viewpoints of which a given body ofknowledge is often recognized as important to their successfullearning. In this paper is proposed a novel approach to Intelli-gent Tutoring System (ITS) applied to Legal domain to addresseach of the above concerns. Then, it was defined an agent-based architecture to support multiple views of domain knowl-edge, improving the quality of student-ITS interactions andthe learning success of the students. Each tutoring agent fromthe system contains a knowledge-based system that combinesCase-Based Reasoning (CBR) and Rule-Based System (RBS).In addition, each agent adopts the Reinforcement Learning Al-gorithm aiming at identifying the best pedagogical strategy byconsidering the student profile. This paper focuses on both ar-chitecture and the mentioned Artificial Intelligence techniquesinto a Legal System.Keywords artificial intelligence and law, intelligent tutoringsystems, case-based reasoning, rule-based systems, reinforce-ment learning.

[1]  Joel R. Tetreault,et al.  Using Reinforcement Learning to Build a Better Model of Dialogue State , 2006, EACL.

[2]  Nicholas R. Jennings,et al.  An adaptive bilateral negotiation model for e-commerce settings , 2005, Seventh IEEE International Conference on E-Commerce Technology (CEC'05).

[3]  Yanghee Kim,et al.  Simulating Instructional Roles through Pedagogical Agents , 2005, Int. J. Artif. Intell. Educ..

[4]  S. Pal,et al.  Foundations of Soft Case-Based Reasoning: Pal/Soft Case-Based Reasoning , 2004 .

[5]  Reinaldo Augusto da Costa Bianchi,et al.  Uso de heurísticas para a aceleração do aprendizado por reforço , 2004 .

[6]  Gerald Tesauro,et al.  Extending Q-Learning to General Adaptive Multi-Agent Systems , 2003, NIPS.

[7]  Vincent Aleven,et al.  Using background knowledge in case-based legal reasoning: A computational model and an intelligent learning environment , 2003, Artif. Intell..

[8]  James Popple,et al.  SHYSTER-MYCIN: a hybrid legal expert system , 2003, ICAIL.

[9]  Enrique F. Castillo,et al.  Expert Systems and Probabilistic Network Models , 1996, Monographs in Computer Science.

[10]  Alneu de Andrade Lopes,et al.  RACIOCÍNIO BASEADO EM CASOS , 1995 .

[11]  Michael L. Littman,et al.  Markov Games as a Framework for Multi-Agent Reinforcement Learning , 1994, ICML.

[12]  Vincent Aleven,et al.  What law students need to know to WIN , 1993, ICAIL '93.

[13]  Georges Span,et al.  LITES, an intelligent tutoring system for legal problem solving in the domain of Dutch Civil law , 1993, ICAIL '93.

[14]  Edwina L. Rissland,et al.  CABARET: Rule Interpretation in a Hybrid Architecture , 1991, Int. J. Man Mach. Stud..

[15]  Tharam S. Dillon,et al.  An example of integrating legal case based reasoning with object-oriented rule-based systems: IKBALS II , 1991, ICAIL '91.

[16]  Anja Oskamp,et al.  PROLEXS divide and rule: a legal application , 1989, ICAIL '89.

[17]  John J. McCarthy,et al.  The Rule Engine for the Java Platform , 2008 .

[18]  R. W. Lee.  Pesquisa jurisprudencial inteligente , 1998 .

[19]  L. Karl Brenting,et al.  Reasoning with portions of precedents , 1991, ICAIL '91.