Artificial Intelligence and Law

, Volume 18, Issue 4, pp 459–479 | Cite as

A new tangible user interface for machine learning document review

  • Caroline Privault
  • Jacki O’Neill
  • Victor Ciriza
  • Jean-Michel Renders


This paper describes a tool for assisting lawyers and paralegal teams during document review in eDiscovery. The tool combines a machine learning technology (CategoriX) and advanced multi-touch interface capable of not only addressing the usual cost, time and accuracy issues in document review, but also of facilitating the work of the review teams by capitalizing on the intelligence of the reviewers and enabling collaborative work.


eDiscovery Litigation Document review Machine learning Categorization Clustering Tangible User Interface Touch-screen User-interface design 


  1. Attfield S, De Gabrielle S, Blandford A (2009) The loneliness of the long-distance document reviewer: e-Discovery and cognitive ergonomics. In: DESI III workshop at ICAIL, Barcelona, June 2009Google Scholar
  2. Barnett T, Godjevac S, Privault C, Renders JM, Wickstrom R (2009) Machine learning classification for document review. In: DESI III Workshop at ICAIL, Barcelona, June 2009 (
  3. Baron J, Braman R, Withers K, Allman T, Daley M, Paul G (2007) Best practices commentary on the use of search & information retrieval methods in e-Discovery. The Sedona Conference Journal 8:189–223Google Scholar
  4. Belkin NJ (2008) Some(what) grand challenges for information retrieval. ACM SIGIR Forum Arch 42(1):47–54CrossRefGoogle Scholar
  5. Blair DC, Maron ME (1985) Evaluation of retrieval effectiveness for a full-text document-retrieval system. Commun ACM 28(3):289–299CrossRefGoogle Scholar
  6. Davis JE, Matus WC (2008) Does your search pass judicial scrutiny? NY Law J.
  7. Gaussier E, Goutte C, Popat K, Chen F (2002) A hierarchical model for clustering and categorising documents. In: Proceedings of the 24th BCS-IRSG European Colloquium on IR research: advances in information retrieval, 25–27 March 2002, pp 229–247Google Scholar
  8. Greenwood A (2007) Attorney at Blah. In: Washington city paper.
  9. Hearst MA (2009) Search user interfaces. Cambridge University Press, CambridgeGoogle Scholar
  10. Hofmann T (1999) Probabilistic latent semantic analysis. In: Proceedings of 15th conference on uncertainty in artificial intelligence. Morgan Kaufmann, pp 289–296Google Scholar
  11. Kershaw A (2005) Automated document review proves its reliability. Digit Discov e-Evid 5(11).
  12. Liddy E (2005) Document retrieval, automatic. In: Encyclopedia of language and linguistics, 2nd edn. Elsevier, AmsterdamGoogle Scholar
  13. Love N (2006) Automating document review. In: CS224n final project
  14. McNee MS, Arnette B (2008) Productivity as a metric for visual analytics: reflections on e-discovery. In: Proceedings of the BELIV’08 conference, Florence, ItalyGoogle Scholar
  15. Roitblat HL, Kershaw A, Oot P (2010) Document categorization in legal electronic discovery: computer classification vs. manual review. JASIST 61(1):70–80Google Scholar
  16. Sebastiani F (2002) Machine learning in automated text categorization. ACM Comput Surv 34(1):1–47CrossRefGoogle Scholar
  17. Smart Document Review (2010)
  18. Tomlinson S, Oard DW, Baron JR, Thompson P (2007) Overview of the TREC 2007 legal track. In: TREC 2007 (
  19. Turtle H (1994) Natural language vs. Boolean query evaluation: a comparison of retrieval performance. In: Proceedings of the 17th ACM SIGIR, Dublin, pp 212–220Google Scholar
  20. Victor Stanley Inc. v. Creative Pipe Inc. 2008 WL 2221841 (D.Md. 2008).

Copyright information

© Springer Science+Business Media B.V. 2010

Authors and Affiliations

  • Caroline Privault
    • 1
  • Jacki O’Neill
    • 1
  • Victor Ciriza
    • 1
  • Jean-Michel Renders
    • 1
  1. 1.Xerox Research Center EuropeMeylanFrance

Personalised recommendations