Generating legal arguments and predictions from case texts

ABSTRACT

In this paper, we present methods for automatically finding abstract, legally relevant concepts in case texts and demonstrate how they can be used to make predictions of case outcomes, given the texts as inputs.In a set of experiments to test these methods, we focus on the open question of how best to represent legal text for finding abstract concepts. We compare different ways of representing legal case texts in order to test whether adding domain knowledge and some linguistic information can improve performance.We found that replacing individual names by roles in the case texts led to better indexing, and that adding certain syntactic and semantic information, in the form of Propositional Patterns that capture a sense of "who did what", led to better prediction. Our experiments also showed that of three learning algorithms, Nearest Neighbor worked best in learning how to identify indexing concepts in texts.In these experiments, we introduced a prototype system that can reason with text cases; it analyzes a case, predicts its outcome considering other cases in the database, and explains the prediction, all starting with a textual description of the case's facts as input.

REFERENCES

• 1: David W. Aha , Dennis Kibler , Marc K. Albert, Instance-Based Learning Algorithms, Machine Learning, v.6 n.1, p.37-66, Jan. 1991 [doi>10.1023/A:1022689900470]
• 2: Vincent A. W. M. M. Aleven, Teaching case-based argumentation through a model and examples, 1997
• 3: Vincent Aleven, Using background knowledge in case-based legal reasoning: a computational model and an intelligent learning environment, Artificial Intelligence, v.150 n.1-2, p.183-237, November 2003 [doi>10.1016/S0004-3702(03)00105-X]
• 4: Ashley, K., and Brüninghaus, S. 2003. A Predictive Role for Intermediate Legal Concepts. In Proceedings of The 16th Annual Conference on Legal Knowledge and Information Systems (Jurix-2003).
• 5: Kevin D. Ashley, Modeling Legal Arguments: Reasoning with Cases and Hypotheticals, MIT Press, Cambridge, MA, 1991
• 6: Boswell, J., and Chapman, R. 1998. Life of Johnson. Oxford, UK: Oxford University Press.
• 7: Stefanie Brüninghaus , Kevin D. Ashley, Toward adding knowledge to learning algorithms for indexing legal cases, Proceedings of the 7th international conference on Artificial intelligence and law, p.9-17, June 14-17, 1999, Oslo, Norway [doi>10.1145/323706.323709]
• 8: Stefanie Brüninghaus , Kevin D. Ashley, Improving the representation of legal case texts with information extraction methods, Proceedings of the 8th international conference on Artificial intelligence and law, p.42-51, May 2001, St. Louis, Missouri, United States [doi>10.1145/383535.383540]
• 9: Stefanie Bruninghaus , Kevin D. Ashley, Predicting outcomes of case based legal arguments, Proceedings of the 9th international conference on Artificial intelligence and law, June 24-28, 2003, Scotland, United Kingdom [doi>10.1145/1047788.1047838]
• 10: Paul R. Cohen, Empirical methods for artificial intelligence, MIT Press, Cambridge, MA, 1995
• 11: Cunningham, C.; Weber, R.; Proctor, J. M.; Fowler, C.; and Murphy, M. 2004. Investigating Graphs in Textual Case-Based Reasoning. In Proceedings of the Seventh European Conference on Case-Based Reasoning (EWCBR-04).
• 12: Daelemans, W.; Zavrel, J.; van der Sloot, K.; and van den Bosch, A. 2004. TiMBL: Tilburg Memory Based Learner, version 5.02. http://ilk.kub.nl/software.html.
• 13: Jody J. Daniels , Edwina L. Rissland, Finding legally relevant passages in case opinions, Proceedings of the 6th international conference on Artificial intelligence and law, p.39-46, June 30-July 03, 1997, Melbourne, Australia [doi>10.1145/261618.261627]
• 14: Dietterich, T. 1996. Statistical Tests for Comparing Supervised Classification Learning Algorithms. Oregon State University Technical Report.
• 15: Claire Grover , Ben Hachey , Ian Hughson , Chris Korycinski, Automatic summarisation of legal documents, Proceedings of the 9th international conference on Artificial intelligence and law, June 24-28, 2003, Scotland, United Kingdom [doi>10.1145/1047788.1047839]
• 16: McCallum, A. K. 2004. Bow: A toolkit for statistical language modeling, text retrieval, classification and clustering. http://www.cs.cmu.edu/~mccallum/bow.
• 17: Thomas M. Mitchell, Machine Learning, McGraw-Hill Higher Education, 1997
• 18: Marie-Francine Moens , Caroline Uyttendaele , Jos Dumortier, Abstracting of legal cases: the SALOMON experience, Proceedings of the 6th international conference on Artificial intelligence and law, p.114-122, June 30-July 03, 1997, Melbourne, Australia [doi>10.1145/261618.261643]
• 19: J. Ross Quinlan, C4.5: programs for machine learning, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1993
• 20: Quinlan, R. 2004. C4.5 Release 8. http://www.rulequest.com/Personal/.
• 21: Riloff, E. 2004. Sundance, Version 4.0. http://www.cs.utah.edu/~riloff.
• 22: Steven L. Salzberg, On Comparing Classifiers: Pitfalls toAvoid and a Recommended Approach, Data Mining and Knowledge Discovery, v.1 n.3, p.317-328, 1997 [doi>10.1023/A:1009752403260]