arshad@cs.ed.ac.uk (Arshad Mahmood) (04/12/91)
Could anybody refer me to any references which apply neural network techniques to law. There is at present a major initiative (both within Britian and elsewhere) to apply techniques from computer science to law (this can range from as an aid to teaching to the actual use of expert systems in arriving at suitable statuates, etc). The problem with most common approaches is that they require a rather rigid area (such as taxation, or immigration) which although being very complex is however relatively routine to actually apply. This is sadly not so with the majority of law, and consequently techniques ranging from logic programming to expert systems are being investigated. It appears to me however that the Anderson/Hinton Associative Memory research would be a great step forward in most of these other areas. We accept that we are in this regard taking a very positivistic view of law, but since this is the way law is commonly taught it doesn't seem unduly harmful at present. I am not a lawyer, therefore this is for a friend who on my advice has taken up at looking into connectionist approaches. We were however not aware of any specific work on this and would be most happy to hear of any relevent work. Regards, A. Mahmood LFCS Edinburgh University Scotland
system@inqmind.bison.mb.ca ( SYSOP ENTITY ) (04/14/91)
I am interested in the application of Neural Networks to Law also. I am a
Forensic Scientist and am currently exploring (albeit tentatively)
potential applications of Neural Networks to decision making in Forensic
Science. Naturally many decisions in Forensic Science are extendable to the
larger context of decision making in law. I understand that at this time
there is a trend in the UK to employ Bayes' Theorem in decision making as it
applies to law. In the course of my own attempts to understand decision
making in Forensic Science I have considered Bayes' Theorem but I do not
find it to be good enough. Neural Networks can be configured to make
decisions that are Bayesian or that employ fuzzy logic, but these are only
limiting cases for specific designed Neural Nets. In fact Neural Networks
in general are capable of much more complex non-linear correlations than can
be achieved by conventional statistical approaches. In this sense they have
the capability to assist us in modelling decision making and also to teach u
s more about how we in fact reach decisions. I am extremely interested in
this area so any dialogue either in this newsgroup or privately is
welcome.
Tod Christianson
______________________________________________________________________________
Tod Christianson "Sysop Entity" at:
478 Beaverbrook St.
Wpg., Mb., Canada THE INQUIRING MIND
R3N-1N3 204-488-1607
USENET:system%inqmind.bison.mb.ca@niven.cc.umanitoba.ca
------------------------------------------------------------------------------ntm1169@dsac.dla.mil (Mott Given) (04/15/91)
From article <8754@skye.cs.ed.ac.uk>, by arshad@cs.ed.ac.uk (Arshad Mahmood): > Could anybody refer me to any references which apply neural network techniques > to law. There is at present a major initiative (both within Britian and > elsewhere) to apply techniques from computer science to law (this can > range from as an aid to teaching to the actual use of expert systems in > arriving at suitable statuates, etc). I can't give you any NN references, but I believe people are having far more success using case-based reasoning. Professor Edwina Rissland at the Univ. of Massachusetts (rissland@cs.umass.edu) is using a case-based approach. From what I understand about neural nets, I believe they are better suited for lower level cognitive tasks than the analysis of legal cases. -- Mott Given @ Defense Logistics Agency Systems Automation Center, DSAC-TMP, Bldg. 27-1, P.O. Box 1605, Columbus, OH 43216-5002 INTERNET: mgiven@dsac.dla.mil UUCP: ...{osu-cis}!dsac!mgiven Phone: 614-238-9431 AUTOVON: 850-9431 FAX: 614-238-9928 I speak for myself
rose@beowulf.ucsd.edu (Dan Rose) (04/17/91)
ntm1169@dsac.dla.mil (Mott Given) writes: >From article <8754@skye.cs.ed.ac.uk>, by arshad@cs.ed.ac.uk (Arshad Mahmood): >> Could anybody refer me to any references which apply neural network techniques >> to law. . . . > I can't give you any NN references, but I believe people are having far > more success using case-based reasoning. Professor Edwina Rissland > at the Univ. of Massachusetts (rissland@cs.umass.edu) is using a > case-based approach. From what I understand about neural nets, I believe > they are better suited for lower level cognitive tasks than the analysis > of legal cases. Well, I suppose that depends what you mean be "more success" and "lower level cognitive tasks." Rissland's work (see, for example the recent Ph.D. thesis by her student Kevin Ashley, published as "Modeling Legal Argument" by MIT Press) focuses on a particular type of legal reasoning task. This is very important, but it is not all there is to AI & Law. In contrast, my own work (with Rik Belew at UCSD) involves the legal research task -- how to find relevant legal documents given a database of (in my system) 4000 court decisions. I am using a combination of neural network and traditional AI techniques. Some lawyers have told me that that my database is too small to be realistic, yet most traditional AI & Law systems handle only 25 to 100 cases. Personally, I think both approaches are needed. In particular, I view legal research systems as a kind of "back end" for legal reasoning systems. But that doesn't mean that one technique is "better" than the other. Dan Rose Computer Science/ Cognitive Science U.C. San Diego -- Dan Rose drose@ucsd.edu
M.Nigri@cs.ucl.ac.uk (MeyerE. Nigri) (04/18/91)
Mr Mahmod: In reply to your message of 11 April 1991. I am using my husbands e-mail to "try" to give you a small hint which I think may help. I am a Phd student at the Department of Commercial Law at Queen Mary College and I am working in the area of Computer Law specifically computer crime. Sometimes, I come across other subjects within the area and one of this was an article on neural network and law. I am not sure if you are looking for technical advice in neural network application to law and I must say that this is not my area of research. I found an article in Rutgers Computer & Technology Law Journal, Vol 16, 1990, which might interest your friend. The title is The Role of Neural Networks in the Law Machine Development, by David R. Warner, Jr. A Conference on Artificial Intelligence & Law will be held on June 25-28 1991 in Oxford and the Society for Computers and Law may be able to give you more details. As far as I know, which is little, there are two PhD thesis so far, in the area of expert systems and law. One is by Richard Susskind, and the other is by David Bainbridge (The Basis, Development and Potential of a Computer System to Assist with the Sentencing of Offenders). As I said I am not able to help you with technical or specific questions to this matter but I hope your friend finds what he is looking for. Regards Deborah Fisch Nigri Queen Mary and Westfield College
rohan@bruce.cs.monash.OZ.AU (Rohan Baxter) (04/20/91)
In <1532@ucl-cs.uucp> M.Nigri@cs.ucl.ac.uk (MeyerE. Nigri) writes: .... >As far as I know, which is little, there are two PhD >thesis so far, in the area of expert systems and law. One is by Richard >Susskind, and the other is by David Bainbridge (The Basis, Development and >Potential of a Computer System to Assist with the Sentencing of Offenders). .... Another expert systems and law Phd dissertation is: An Artificial Intelligence Approach to Legal Reasoning Anne von der Lieth Gardner Stanford Uni, June 1984 -- ---------------------------------------------------------------------- Rohan Baxter, rohan@bruce.cs.monash.edu.au