A machine learning approach to prior case retrieval

ABSTRACT

We describe a system that processes court opinions and retrieves related cases from a citator database, so that new cases can be linked to earlier ones that they impact. The design of the system combines information extraction, information retrieval and machine learning techniques in a novel way. The fully implemented program is capable of performing prior case retrieval at human levels of recall and acceptable levels of precision.

REFERENCES

• 1: Peter Jackson , Khalid Al-Kofahi , Chris Kreilick , Brian Grom, Information extraction from case law and retrieval of prior cases by partial parsing and query generation, Proceedings of the seventh international conference on Information and knowledge management, p.60-67, November 02-07, 1998, Bethesda, Maryland, United States [doi>10.1145/288627.288642]
• 2: John E. Hopcroft , Jeffrey D. Ullman, Introduction To Automata Theory, Languages, And Computation, Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 1990
• 3: V. I. Levenshtein (1966). Binary codes capable of correcting deletions, insertions and reversals. Sov. Phys. Dokl., 6, pp. 707- 710
• 4: Vladimir N. Vapnik, The nature of statistical learning theory, Springer-Verlag New York, Inc., New York, NY, 1995
• 5: Amit Bagga , Alan W. Biermann, Coreference, cross-document coreference, and information extraction methodologies, 1998
• 6: Khalid Al-Kofahi , Brian Grom , Peter Jackson, Anaphora resolution in the extraction of treatment history language from court opinions by partial parsing, Proceedings of the 7th international conference on Artificial intelligence and law, p.138-146, June 14-17, 1999, Oslo, Norway [doi>10.1145/323706.323788]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL

General Terms:
Design, Experimentation, Theory

Keywords:
case retrieval, party name matching, support vector machines