"[T]he dichotomy between rule based systems and cased based reasoning systems in AI and law research reflects an underlying jurisprudential debate that has raged for the last century. ... Instead of implying that legal reasoning is primarily a process of deduction or a process of analogising the theory of law as discourse requires a richer view of the process of legal reasoning." - Michael Aikenhead

Introductory Readings

AI am the law. The Economist Technology Quarterly (March 12, 2005 issue date; pages 34 - 46; posted online March 10, 2005). "Given the choice, who would you rather trust to safeguard your future: a bloodsucking lawyer or a cold, calculating computer? Granted, it's not much of a choice, since neither lawyers nor computers are renowned for their compassion. But it is a choice that you may well encounter in the not-too-distant future, as software based on 'artificial intelligence' (AI) starts to dispense legal advice. Instead of paying a lawyer by the hour, you will have the option of consulting intelligent legal services via the web. While this might sound outlandish, experts believe that the advent of smart software capable of giving good, solid legal advice could revolutionise the legal profession. ... What makes both these programs so smart is that they do more than just follow legal rules. Both tasks involve looking back through past cases and drawing inferences from them about how the courts are likely to view a new case. To do this, the programs use a combination of two common AI techniques: expert systems and machine learning. ... [S]mart software has the potential to make legal advice more readily available, unnecessary court battles less frequent, and rulings more consistent."

Divorce Software Designed to Handle Negotiations. By Melinda Wenner. LiveScience (July 31, 2007). "Divorce is never pleasant, but new software is aimed at making the process a little less harrowing. The computer program combines artificial intelligence, game theory and an electronic or human external mediator to help divorcing couples settle their disputes in a fair and rational manner -- and hopefully with fewer gray hairs. The new software is a fresh incarnation of a project going back to 2004, when Emilia Bellucci and John Zeleznikow from Victoria University in Australia developed 'Family Winner' to help couples settle divorce disputes by focusing on compromise. ... While 'Family Winner' successfully met the needs of both husband and wife, it wasn't always fair to the needs of third parties, like children, according to Bellucci and Zeleznikow. So, to address this problem, they developed new software called 'Family Mediator.' As the name implies, the software relies on a mediator -- either a family law practitioner or an electronic decision support system...."

• Also see this information aboutFamily Winner.

Cornell lawyers and computer experts team up to make government rule-making accessible in Internet age. By Bill Steele. Cornell Chronicle Online (May 16, 2007). "To help the agencies deal with rule-making in the Internet age and make the process more accessible to the public, Cornell scientists and legal experts have created the Cornell e-Rulemaking Initiative (CeRI), funded by a $750,000, three-year grant from the National Science Foundation.... The potential of the Internet has some regulators worried. A proposed rule about organic-food labeling, for example, generated some 400,000 e-mail comments. A Federal Communications Commission rule about the consolidation of media ownership brought in over 2 million comments. Such extremes have been rare, but since regulators are required to consider every submission and respond to major points, they are asking for help.[Claire] Cardie, an expert in natural language processing, is developing computer programs to sift and categorize the masses of comments. First, agency staff will highlight sentences in the comments that connect with various issues. Over time, the computer will learn the rules of classification and take over.'People can classify all of the phrases and sentences in about 40 to 50 comments per day, depending on length,' Cardie says. 'Software takes just seconds to classify all of the phrases and sentences in one document.'"

Xerox Aims to Improve Search Results - Xerox has developed FactSpotter, a search tool that analyzes written language rather than looking for keywords. By Peter Sayer. IDG News Service | PC World (June 21, 2007). "The tool, FactSpotter, analyzes the underlying grammar of a text in order to infer additional information, such as whether ambiguous words are being used as nouns or verbs, or to whom a pronoun refers, said Fridirique Segond, who manages the parsing and semantics research group at Xerox Research Center Europe near Grenoble, France. ... One of the first groups to use FactSpotter will be Xerox Litigation Services, which next year will build it into a suite of 'e-discovery' software for the legal profession, Segond said."

• Visit Xerox Research Centre Europe (XRCE).

Robo-justice - Do we have the technology to build a better legal system? By Drake Bennett. The Boston Globe (September 11, 2005). "Computer judges, of course, aren't going to be ascending to the bench in the foreseeable future. 'Nobody thinks that's a good idea,' says Carole D. Hafner, a Northeastern University computer scientist and pioneer in using artificial intelligence to study the law. Judging, and most especially Supreme Court judging, is a complex and subtle mix of imagination, acuity, and political calculation. Still, at a time when doctors are starting to use software to aid in their diagnoses and when hedge funds are using computer models to make multibillion-dollar investment decisions, there is growing interest -- even in an American legal establishment usually resistant to change -- in finding ways to incorporate artificial intelligence into the law. ... Put simply, artificial intelligence is the branch of computer science that deals with getting machines to think like human beings. Its application to the law dates, in its earliest form, to the 1950s, when mathematicians first tried to use formal logic to model legal reasoning. ... Some of the fruits of this fascination, however, have been decidedly practical, from intelligent document retrieval systems that use fuzzy logic to search not just by keyword but by concept (the only AI application widely used in American law firms) to programs that predict the outcomes of court cases or evaluate potential clients."

Logging On to Your Lawyer. By Duncan Graham-Rowe. Technology Review (Febuary 2005). "Manufacturing, finance, and the communications industry have in the last decade all come to rely upon artificial intelligence. But theres one industry that continues to put up resistance: the legal profession. The idea of a machine making legal decisions was long considered by opponents to be dangerous and ethically untenable. Thats about to change, says John Zeleznikow, a computer scientist at Victoria University in Melbourne, Australia. Zeleznikow believes AI is about to improve peoples access to justice and massively reduce the costs of running legal services."

Seller of Software Used in Bankruptcy Petitions Held ‘Preparer.’ By Tina Bay. Metropolitan News-Enterprise (February 28, 2007). "The seller of web-based software used to prepare bankruptcy petitions qualifies as a 'bankruptcy petition preparer' subject to the requirements of the U.S. Bankruptcy Code, the Ninth U.S. Circuit Court of Appeals ruled yesterday. The court unanimously agreed with a Ninth Circuit Bankruptcy Appellate Panel that now-defunct Ziinet.com owner and operator Henry Ihejirika violated 11 U.S.C. Sec. 110, which imposes certain obligations on bankruptcy petition preparers and penalizes negligent or fraudulent preparation. The court also affirmed the BAP’s conclusion that Ihejirika had engaged in the unauthorized practice of law. ... One of the sites owned and operated by Ihejirika was the 'Ziinet Bankruptcy Engine,' which represented itself to prospective customers as being 'an expert system' and claimed to 'know [ ] bankruptcy laws right down to those applicable to the state' in which the particular user lived."

• The Reynoso v. Frankfort Digital Services, Ltd. opinion is avaiable from the United States Court of Appeals for the Ninth Circuit. Be sure to see footnote 9: "... we express no view as to whether software alone, or other types of programs, would constitute the practice of law."
• Also see this article: Beware the Unauthorized Practice of Law in Cyberspace. By Shari Claire Lewis. New York Law Journal / available from Law.com (June 6, 2007). "Consider the recent decision by the 9th U.S. Circuit Court of Appeals in In re Reynoso [fn]. ... Frankfort sold access to Web sites where customers could access browser-based software for preparing bankruptcy petitions and schedules, as well as informational guides promising advice on various aspects of relevant bankruptcy law. Included in the site was the following representation: 'Ziinet is an expert system and knows the law. Unlike most bankruptcy programs which are little more than customized word processors the Ziinet engine is an expert system. It knows bankruptcy laws right down to those applicable to the state in which you live.' ... The circuit [court] concluded that Frankfort had engaged in the unauthorized practice of law. It observed that Frankfort's sites offered extensive advice on how to take advantage of so-called loopholes in the Bankruptcy Code, promised services comparable to those of a 'top-notch bankruptcy lawyer,' and described its software as 'an expert system' that would do more than function as a 'customized word processor.' Moreover, the appellate court added, the software went 'far beyond providing clerical services.' It determined where (particularly, in which schedule) to place information provided by the debtor, selected exemptions for the debtor, and supplied relevant legal citations. Providing such personalized guidance amounted to the practice of law, the appellate court held."

2016: Diary of the Last Lawyer (alternative future scenario). From the Final Report (2002) of the ABA Committee on Research About the Future of the Legal Profession. "Sensing an opportunity, several enterprising technologists developed an artificial intelligence program. This AI program could achieve justice and be fair without the bias inherent in every human being, including judges. It could deliver results far more cheaply than humans. Other technology was developed simultaneously that could literally detect and determine the veracity of the inputted facts. The truth was knowable - by machines. Society accepted the verdict of the machines because truth could be determined, whether in criminal or civil matters."

• As noted in the report: "In its second year, the Committee worked with legal futurist Stuart A. Forsyth to envision the preferred future of the legal profession and to determine action steps that would foster that future. You can visit Stuart A. Forsyth's web site and read his scenario of a "probable, alternative future:" 2020: Justice By the People: "Technological strides have pervaded the practice of law as well. The artificial intelligence expert systems research from the 1980s was first applied to medical diagnostic systems in the 1990s, reaching AMA and public acceptance by the end of the first decade of the New Millennium. Similar work was done in the law, as A-I scientists explored how lawyers analyze legal problems and prepare arguments for their clients and how judges rule on objections and motions and decide cases. Tentatively at first, both lawyers and judges began to use these systems ...."

A Discourse on Law and Artificial Intelligence. By Michael Aikenhead. 5 Law Technology Journal 1 (1996).

Victorian Law Reform Committee of the Parliament of Victoria, Australia. "13.10: The earliest uses of AI in law can be traced back to the 1950s with the development of basic legal information retrieval systems, which replicated aspects of human intelligence, including memory and recognition of symbols. The 1970s saw the development of a number of legal intelligence systems to aid lawyers draft documents, establish appropriate causes of action and to determine whether the legal elements of a particular statute were met. While early systems 'failed to account for the complexity and subtlety of the law and legal reasoning', research and applications in the area have progressively become more sophisticated. AI techniques used in law include logic programming, neural networks and case-based reasoning."

Kevin D. Ashley's Syllabus - Seminar on Artificial Intelligence and Law. February 2007. Selected readings for over ten topics. Kevin Ashley is a Professor of Law at the University of Pittsburgh School of Law, a Professor of Intelligent Systems at the University of Pittsburgh's Graduate Program in Intelligent Systems (ISP), a Senior Scientist at the University of Pittsburgh's Learning Research and Development Center, and an AAAI Fellow.

• Also see:
  • Kevin Ashley's position paper for the AAAI 2006 Fellows Symposim: "I have been interested in using AI computational models of case-based reasoning empirically to investigate semantic relationships between abstract normative principles and fact-specific cases. Moral and legal philosophers have long observed a dialectical relationship between them: the abstract principles inform the decisions of specific cases, but the decisions, in turn, elaborate the principles’ meaning. I thank my dissertation adviser, Edwina Rissland, for 'turning me on' to this insight a long time ago (See Ashley & Rissland, 2003, p. 31)."
  • Kevin Ashley's research projects including:
    • Hypothesis Formation and Testing in an Interpretive Domain: a Model and Intelligent Tutoring System
    • Case-Based Reasoning Research Group

The Potential of Artificial Intelligence to Help Solve the Crisis in Our Legal System. Donald H. Berman and Carole D. Hafner. Communications of the ACM, August 1989; Volume 32, Issue 8.

IT unravels tangled legal webs. The Australian (November 10, 2004, page B08; subscription req'd.). "Remote dispute resolution is a fast-growing field that could provide a new direction for tech-savvy students. ... Melissa Conley Tyler, program manager at the International Conflict Resolution Centre at the University of Melbourne, says online dispute resolution is booming. There are now 115 online dispute resolution services worldwide that have resolved more than 1.5million disputes. Conley Tyler, who convened the third UN annual forum on online dispute resolution (ODR) at Melbourne University earlier this year, believes it is a field that could provide many job opportunities for a generation of technologically literate law students. ODR uses online and video conferencing and even artificial intelligence to facilitate negotiations. ... While Australian universities do not offer degrees in ODR, several universities have short courses. Bond University runs a semester-long course in online dispute resolution as part of its master of dispute resolution and master of laws."

• The Role of Artificial Intelligence in Online Dispute Resolution, by Arno R. Lodder and Ernest M. Thiessen. Papers and Proceedings of the 2003 United Nations Forum  on ODR. Abstract: "In all ODR-procedures, Information Technology (IT) is used. Artificial Intelligence (AI) applications are a subset of IT applications and add benefit either by using 'intelligent techniques' or by 'simply' performing in an intelligent way. In this paper the (possible) use of AI in ODR is addressed. Two negotiation systems, SmartSettle and Family_Winner, are described and compared. An argument support tool for arbitration is also described, and it is argued that this tool could also be used in negotiation systems. A discussion of automated translation, automated summarizing, computer-mediated legal argument, and intelligent agents completes this paper on what AI can do for ODR."
• More resources are available from ODR info at the UMass Center for Information Technology and Dispute Resolution, including a collection of working papers.

General Readings

Collections, Journals & Special Issues

Artificial Intelligence and Law: Journal Homepage. Published by Springer. "Artificial Intelligence and Law is an international forum for the dissemination of original interdisciplinary research in the following areas: *Theoretical or empirical studies in artificial intelligence (AI), cognitive psychology, jurisprudence, linguistics, or philosophy which address the development of formal or computational models of legal knowledge, reasoning, and decision making.*In-depth studies of innovative artificial intelligence systems that are being used in the legal domain.*Studies which address the legal, ethical and social implications of the field of Artificial Intelligence and Law."

International Journal of Law and Information Technology. Oxford Journals, Oxford University Press. "Featuring up-to-date coverage of computer law as well as the application of computer technology to legal practice, this journal is designed to be of use to both lawyers and computer specialists." See, for example:

• An Artificial Intelligence System Suggests Arbitrariness of Death Penalty. By Stamos T. Karamouzis and Dee Wood Harper. Advance Access published online on August 13, 2007.
• A Knowledge Representation Model for the Intelligent Retrieval of Legal Cases. By Yiming Zeng, Ruili Wang, John Zeleznikow, and Elizabeth Kemp. Int J Law Info Tech 2007 15: 299-319.

Journal of Information, Law and Technology (JILT) published by The Electronic Law Journals Project, Warwick Law School, The University of Warwick. Among the articles you'll discover here are:

• A Computer Supported Environment for the Teaching of Legal Argument. By T. J. M. Bench-Capon, P. H. Leng, and G. Staniford. 1998, Issue Three.
• The Revolution in Legal Information Retrieval or: The Empire Strikes Back. By Erich Schweighofer. 1999, Issue One.

Jurix Proceedings Archive - papers from Jurix's international conference on Legal Knowledge and Information Systems, which has been held every year since the first conference in 1988.

Proceedings of the AISB 2002 Symposium on Artificial Intelligence and Legal Reasoning. One of the many convention proceedings available from The Society for the Study of Artificial Intelligence and Simulation of Behaviour (SSAISB).

Proceedings of the International Conference on Artificial Intelligence & Law (ICAIL).

• The proceedings of ICAIL 2005, the Tenth International Conference on Artificial Intelligence and Law,are available from the International Association for Artificial Intelligence and Law.:
• The proceedings of the first nine conferences (1987 - 2003) are available from the ACM Digital Library. That's where you'll find articles such as:
  • Advisory systems for pro se litigants. By L. Karl Branting (ICAIL '01)
  • Making Way for Intelligence in Case Space. By Philip Greenspun and Marc Lauritsen. (ICAIL '95)

Symposium - Artificial Intellegence and Judiciary Proofs. 22 Cardozo Law Review, Issues 5 - 6 (July 2001).

Articles

Legal knowledge based systems: some observations on the future. By Michael Aikenhead. Web Journal of Current Legal Issues (1995). Among the subjects covered are expert systems, case based reasoners, neural networks, fuzzy logic, and non-monotonic logic.

Integrating Artificial Intelligence, Argumentation and Game Theory to Develop an Online Dispute Resolution Environment. By Emilia Bellucci, Arno R. Lodder, and John Zeleznikow. 16th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'04) at pages 749-754. "Current research in developing negotiation support systems focuses upon argumentation, artificial intelligence and game theory. These techniques are rarely used in tandem. We argue that truly intelligent negotiation support systems require the integration of such techniques." This paper is available from the publication collection of Arno R. Lodder of the Computer Law Institute, Vrije Universiteit Amsterdam.

Automating Judicial Document Drafting: A Discourse-Based Approach. By Karl Branting, James Lester, and Charles Callaway. In Artificial Intelligence & Law, 6(2-4), pp. 111-149 (1998). "This paper proposes a model in which the drafter's goals and the stylistic and discourse conventions are represented in a discourse structure consisting of a tree of illocutionary and rhetorical operators with document text as leaves. ... The applicability of this model to a representative set of judicial orders -- jurisdictional show-cause orders -- is demonstrated by illustrating (1) the analysis of show-cause orders in terms of discourse structures, (2) the derivation of a document grammar from discourse structures of two typical show-cause orders, and (3) the synthesis of a new show-cause order from the document grammar." - from the Abstract.

Robot, Esq. By Krysten Crawford. Forbes Magazine (October 2, 2000). " It's everyone's fondest dream: a computer that will do your legal work and won't bill you at $400 an hour. Sorry, it's not about to happen anytime soon. But then there's Frederic Parnon, a former Manhattan litigator who left his firm five years ago to develop software that can be used to give legal advice of sorts. Working from a cramped, nondescript lab above Rockefeller Center, Parnon has spent more than $1 million of his own moneycreating a program called Jnana, which means 'knowledge' in Sanskrit. Already, a handful of companies and law firms, such as General Electric, J.P. Morgan and Davis Polk & Wardwell, have bought the program and customized it for their needs. ... While the best of these programs are more than mere databases, they can't replicate the level of reasoning and finesse that lawyers are expected to supply. For now they're best for routine, narrow areas that are highly regulated--like environmental or securities law. "... But Parnon and others say the main advantage of a virtual lawyer system is to avoid costly litigation by spreading legal advice to workers down the ranks. ... All of this raises legal ethical questions that bar associations have yet to resolve. Computers, for instance, aren't licensed to practice law--so who's responsible for bum advice?"

An Introduction to Artificial Intelligence and Legal Reasoning: Using xTalk to Model the Alien Tort Claims Act and Torture Victim Protection Act. By Eric Allen Engle. Richmond Journal of Law and Technology (Volume XI, Issue 1, Fall 2004). Abstract: "This paper presents an introduction to artificial intelligence for legal scholars and includes a computer program that determines the existence of jurisdiction, defences, and applicability of the Alien Tort Claims Act and Torture Victims Protection Act. The paper includes a discussion of the limits and implications of computer programming in formal representations of the law. Concluding that formalization of the law reveals implicit weaknesses in reductionist legal theories, this paper emphasizes the limitations in practice of such theories." You can download Mr. Engle's Program, ATCA, via a link on the index page.

Trial by laptop - An electronic judge on wheels delivers instant justice. By Duncan Graham-Rowe New Scientist (April 29, 2000; Issue 2236; subscription req'd.). "There's been a minor car crunch on a city street in Brazil, and the two drivers are screaming and gesticulating, arguing angrily over who's to blame and who should pay for the damage. Suddenly, a van screeches to a halt and out pop a judge, a court clerk and a very special laptop computer. Instant justice has arrived, cyber-style. This is no fantasy. The laptop runs an artificial-intelligence program called the Electronic Judge, and its job is to help the human judge on the team swiftly and methodically dispense justice according to witness reports and forensic evidence at the scene of an incident. It can issue on-the-spot fines, order damages to be paid and even recommend jail sentences."

• Also see: 'E-Judge' Hits the Streets - Justice Goes High Tech in Brazil. By Antonio Brasil. Special to ABCNEWS.com. Rio De Janeiro, Brazil (May 12, 2000). "Currently in a test phase on the city streets of Brazil, the Electronic Judge is part of a new project called Justice-On-Wheels. It's designed to make the judicial process more efficient by sending a judge, laptop in tow, to a minor crime or accident scene to render a decision on the spot after processing case facts. ... Written in Visual Basic, the Electronic Judge processes the simple 'yes' or 'no' answers from the involved parties and eyewitnesses. It then writes a report with possible solutions for the case according to Brazil's legal code. The judge evaluates this report, and if the judge and involved parties agree, settlement is reached on the spot."

Legal Reasoning Models. By Carole D. Hafner. (2001). In International Encyclopedia of The Social and Behavioral Sciences, Elsevier Science Publishers. "With the advent of computers and artificial intelligence, both the range of techniques available and the practical motivation for creating legal reasoning models have grown. Rule-based systems using logical inference techniques have been developed and used successfully in a number of legal domains, especially those dominated by complex regulations, such as taxation and social benefits administration." (Also see her home page for additional articles and resources.)

• Visit the DolphinSearch Litigation Support page to see how their "eDiscovery provides a variety of tools to recognize important documents, including simple and advanced Boolean searching, metadata searches, and neural-network-based concept searching. Our patented concept search that identifies documents by meaning, even if the key terms for which you are searching are not actually in the document."

A Review of TRACFed - Lawyers Strike Gold Mining Government Data. By Patricia Hassett and Linda Roberge. Law Library Resource Xchange (October 15, 2002). "Lawyers, along with other professionals, are looking at the many advantages that information technology holds for their profession. In this paper we discuss a new class of information that goes beyond databases to the realm of data warehouses and data mining. These state-of-the-art technologies and the information they produce promise to redefine some of the best-practice standards of the legal profession. ... Before giving advice based upon a perception of how the system works, careful lawyers would like to know whether their personal perceptions are consistent with actual facts. TRACFed allows lawyers to confirm their impressions with actual data. Do cases really move more slowly through Judge Smith's court? How frequently does a particular prosecutor decline certain types of cases? What is the likelihood that my client's tax return will be audited? How often do criminal cases investigated by a particular agency result in a conviction?"

Creating an Environment in Law Firms Where Artificial Intelligence and Knowledge Management Will Work. By Dennis Kennedy. [Author's note: " I prepared the original version of this paper was prepared for the Workshop entitled 'Legal Knowledge Systems in Action: Practical AI in Today's Law Office" at the 2001 ICAIL (International Conference on Artificial Intelligence and the Law)"]. "This paper will discuss some of the needs that law firms want to address with artificial intelligence and knowledge management projects, the resistance barriers in law firms, and then move on to list some attractive target areas for these approaches and factors that will contribute to success of these types of projects."

AI, Decision Science, and Psychological Theory in Decisions About People: A Case Study in Jury Selection. By Roy Lachman. AI Magazine 19(1): Spring 1998, 111-129. "AI theory and its technology is rarely consulted in attempted resolutions of social problems. Solutions often require that decision-analytic techniques be combined with expert systems. The emerging literature on combined systems is directed at domains where the prediction of human behavior is not required. A foundational shift in AI presuppositions to intelligent agents working in collaboration provides an opportunity to explore efforts to improve the performance of social institutions that depend on accurate prediction of human behavior."

Search engines take the stand. By Declan McCullagh. CNET News.com (May 13, 2004). "[Manuel] Rodriguez finished his sentence before his new trial could take place. But his case nevertheless offers a striking illustration of the growing clout of Internet search engines among the judiciary--a controversial trend that's so far garnered little attention outside legal circles. In the United States and abroad, judges are turning to search engines such as Google to check facts, to look up information about companies embroiled in litigation, and to challenge statistics presented by attorneys in court. Dozens of judges have penned opinions describing Google as a valuable--and sometimes crucial--source of knowledge. ... Some legal experts warn that Google searches are no substitute for the painstaking process of evidence and testimony. ... Rules governing out-of-court research are ambiguous about the use of search engines and, in the United States, tend to vary by state."

2004 KMWorld Promise and Reality Finalists. By Hugh McKellar. KMWorld (November / December 2004; Volume 13, Number 10). "Thomson Elite- West km from Thomson Elite utilizes the artificial intelligence CaRE (categorization and routing engine) technology to automatically classify law firm documents, which allows firms to leverage their best thinking and experience by collecting and reusing their intellectual assets."

• Also see: Westlaw Service Gains ‘Smart Tools.' Information Today Weekly News Digest (January 31, 2005). "Thomson West ... has added 'Smart Tools' to its Westlaw online research service. ... Smart Tools use artificial intelligence technology developed in-house by technologists, scientists, and attorneys solely focused on the legal industry."

JUSTICE: A Judicial Search Tool Using Intelligent Concept Extraction. By James Osborn and Leon Sterling, Intelligent Agent Laboratory, Department of Computer Science and Software Engineering, University of Melbourne. (Presented at AustLII's "Law Via The Internet '99" conference.) Abstract: "A legal knowledge based system called JUSTICE is presented which provides conceptual information retrieval for legal cases. JUSTICE can identify heterogeneous representations of concepts across all major Australian jurisdictions. The knowledge representation scheme used for legal and common sense concepts is inspired by human processes for the identification of concepts and the expected order and location of concepts. The knowledge is supported by flexible search functions and string utilities. JUSTICE works with both plaintext and HTML representations of legal cases over file systems, and the World Wide Web. In creating JUSTICE, an ontology for legal cases was developed, and is implicit within JUSTICE. The identification of concepts within data is shown to be a process enabling conceptual information retrieval and search, conceptualised summarisation, automated statistical analysis, and the conversion of informal documents into formalised semi-structured representations. JUSTICE was tested on the precision, recall and usefulness of its concept identifications and achieved good results. The results show the promise of our approach to conceptual information retrieval and establish JUSTICE as an intelligent legal research aid offering improved multifaceted access to the concepts within legal cases."

• Also see: Automated Concept Identification within Legal Cases. By James Osborn and Leon Sterling. The Journal of Information, Law and Technology (JILT) 1999(1).

A Pragmatic Legal Expert System. By James Popple. Applied Legal Philosophy Series, Dartmouth (Ashgate), Aldershot (1996). Excerpt from the abstract: "SHYSTER is a case-based legal expert system (although it has been designed so that it can be linked with a rule-based system to form a hybrid legal expert system). Its advice is based upon an examination of, and an argument about, the similarities and differences between cases. SHYSTER attempts to model the way in which lawyers argue with cases, but it does not attempt to model the way in which lawyers decide which cases to use in those arguments. Instead, it employs statistical techniques to quantify the similarity between cases. It decides which cases to use in argument, and what prediction it will make, on the basis of that similarity measure."

• The book is out of print, but can be downloaded without charge from these sites:
  • The Australian National University
  • Google Book Search
  • Internet Archive
  • Live Search Books
• Also see FINDER

Artificial Intelligence and Legal Reasoning: A Discussion of the Field and Gardner’s Book. By Edwina Rissland. AI Magazine 9(3): Fall 1988, 45-55. "Legal reasoning is an intriguing field for the researcher in artificial intelligence because it demands that many deep and nettlesome problems, for instance, those of knowledge representation and analogy, be addressed head on. It presents a range of interesting reasoning skills, some of which seem tantalizingly tractable with currently well-understood methodologies such as those of expert systems, and others of which seem to subsume exceedingly hard problems such as natural language understanding. The law is an attractive domain for AI research for several reasons. First, it has a tradition of examining its own reasoning process. Second, its reasoning is stylized; in Anglo-American common law, one reasons according to stare decisis, or the doctrine of precedent, in which similar cases are to be decided similarly. Central aspects of such reasoning involve analogy and reasoning with cases. Third, much of the knowledge is readily accessible and some of it is very well structured and codified."

Artificial Intelligence and The Law: How to Develop a Rule-Based Legal Expert System in Prolog [excerpt]. By Francisco Eymael Garcia Scherer. PC AI (17.3). "This article demonstrates the key techniques for developing a rule-based legal expert system. It also introduces the reader to basic aspects of PROLOG, such as goal-oriented programming, backtracking and the interaction between PROLOG facts and variables."

Knowledge Management in Legal Departments. A collection of articles from R.G. Smith & Associates, including articles such as:

• Share the Wealth: what 'knowledge management' could mean to your legal department. American Bar Association, Business Law Today, Volume 13, Number 2 - November/December 2003.
• Knowledge Management in a Multinational Law Department – The Schlumberger "LawHub." Presented at ACCA Annual Meeting on "Knowledge Management/Knowledge Networking in the Corporate Law Department", October 9, 2003.

Some online papers about artificial intelligence and law by Alan L. Tyree, Australasian Legal Information Institute (a joint facility of the University of Technology Sydney and the University of New South Wales Faculties of Law): FINDER - an expert system in law; The DataLex Project; Will Justice Fall to Bits?; Generating Legal Arguments; Legal Expert Systems - the problem of precedent.

• Also see SHYSTER.

Related Resources

Artificial Intelligence and the Law Resource Center - Starting Points for Finding AI and the Law Resources on the Internet. Maintained by Dennis Kennedy.

Ask ALEX. Available from JURIST. "ALEX is an AI-based 'bot' programmed to help you locate basic legal information online. But be warned - she's very experimental, and she sometimes has a bit of an attitude! ... ALEX cannot provide legal advice. If you have a legal problem, consult a lawyer."

CATO, SMILE, SIROCCO and PETE. From the Case-Based Reasoning Research Group at the University of Pittsburgh. "CATO was developed by Vincent Aleven. It is an intelligent environment for teaching skills of making arguments with cases to law students. CATO is based on HYPO's model of case-based argumentation, but also includes a number of new ideas. ... SMILE is the research project of Stefanie Bruninghaus. SMILE is a system to help automatically index legal cases for a CBR system like CATO. ... The research on SIROCCO was carried out by Bruce McLaren.... SIROCCO is a case-based retrieval and analysis system used for retrieving and analyzing engineering ethics cases. The objective and focus of this work has been to develop techniques for bridging the gap between abstractly defined rules and the specific facts of cases. ... Like SIROCCO, the PETE project is concerned with reasoning about ethics. PETE is the PhD project of Ilya Goldin. It is a web-based tutoring program, designed to help students practice using the skills involved in case analysis." Also see their collection of publications.

"The Computer Law Institute is part of the Faculty of Law of the Vrije Universiteit ('Free University') of Amsterdam, the Netherlands. The core activities of the CLI are research and education of 1) computer science applied in the legal field and 2) legal implications of information technology."

• ICAIL Conferences:
  • Ninth International Conference on Artificial Intelligence and Law (ICAIL 2003)
  • Eigth International Conference on Artificial Intelligence and Law (ICAIL 2001)
• ICAIL Proceedings
  • ICAIL 2005
    • conference
    • workshops (the electronic versions are free)
• ICAIL 1987 - 2003

IBM® Classification Module for OmniFind™ Discovery Edition. "The IBM Classification Module is a platform for a wide range of applications that require large amounts of unstructured content to be appropriately categorized and tagged. These applications range from email classification, auto-response and archive tagging to compliance and legal discovery to document classification and taxonomy management within Enterprise Content Management (ECM) systems. ... Legal Discovery:The need for organizations to be prepared for legal discovery is increasing. The newly amended Federal Rules of Civil Procedure require that an organization be prepared to respond to legal notifications that may require the production of electronic information as well as paper based records.The IBM Classification Module can help you to both proactively organize your electronic content as well as dynamically locate and prioritize content during the review process. Lawyers are expensive knowledge workers. By organizing case content in a contextually aware manner, you can make them as efficient as possible. ... Features and Capabilities ... * Analyzes unstructured content and metadata to assign categories* Reads and understands full text of content regardless of misspellings, abbreviations, acronyms, and other quality-of-content issues* Self-learning algorithms that incorporate feedback to improve and adapt classification over time ..."

Jurix: "The Foundation for Legal Knowledge Based Systems (Jurix) is a forum for researcher in the field of Law and Computer Science in the Netherlands and Flanders. Its members are research groups from most Dutch universities and a Flemish university, KU Leuven. Jurix also has affiliated members, mostly consisting of people who used to work at one of the Jurix member sites.Jurix organises quarterly meetings that comprise of a number of lectures on AI and Law topics from both academics and practitioners. These meetings are open to all. Since 1988, Jurix has held annual international conferences on Legal Knowledge and Information Systems." Conference papers are available electronically from the Jurix Proceedings Archive.

JustSys. "JustSys Pty Ltd [founded by founded by three researchers, Andrew Stranieri, John Yearwood and John Zeleznikow] is dedicated to the rapid development of web-based support systems that model decision-making reasoning. Decision-support systems guide users to make better decisions, in less time and with more consistency. The decision support software tools and methodologies JustSys Pty Ltd deploys have evolved from research projects in the application of artificial intelligence to law conducted in two universities over the last five years."

Legal Machines Project: led by Selmer Bringsjord, Dave Ferrucci, and Allan Silver. "Legal expert systems are intended to be as smart as Deep Blue, but rather more helpful. ... Our intuition is that people won't mind in the least if their lawyers are empowered by artificial colleagues--quite the contrary, if they are the beneficiaries of quicker turnaround time, lower legal fees and higher quality work product."

Legal Ontologies and Artificial Intelligence Techniques Workshop (LOAIT), June 6, 2005, held in conjunction with ICAIL-05?. "In the last few years Legal Informatics (the study of methods for automating the treatment of legal information) has been significantly influenced by Artificial Intelligence (AI) approaches. For instance, Machine Learning techniques have successfully been applied to problems of legal documents classification, legal information retrieval, legal knowledge discovery and extraction.As the use of these techniques becomes more widespread it also becomes clearer how to enhance their performances. One way of doing this is to employ structured (domain) knowledge in order to reduce complexity and support correct reasoning. Legal Ontologies are playing a crucial role in providing such knowledge at various levels of specificity and formality."

• The workshop proceedings are available from IAAIL.

Leibniz Center for Law: "The Leibniz Center for Law has its roots in the former department of Computer Science & Law of the Law Faculty of the University of Amsterdam.... The Leibniz Center conducts research and provides education in the field of Artificial Intelligence and law. We focus on the development and application of techniques from Artificial Intelligence to the field of Law for the purpose of supporting legal practice, and bringing new insights to legal theory. The Leibniz Center for Law has longstanding experience on legal ontologies, automatic legal reasoning and legal knowledge-based systems, (standard) languages for representing legal knowledge and information, user-friendly disclosure of legal data, and the application of ICT in education and legal practice (e.g. CASE). It plays an important role in the development of eGovernment on both national and international level. The center provides advice on change-management issues of knowledge-intensive legal processes and the improvement of knowledge-productivity in legal organisations." Be sure to check out their many exciting projects and publications.

The Regnet Project. Stanford University. "The Regnet research work so far has focused on developing tools and formalisms for making environmental regulations more accessible to interest groups and the public. The approach has been to process regulations into a standardized, machine-comprehendible format that can be easily augmented with new information. This foundation can be exploited for a number of tasks, from searching to reasoning."

• Logic-Based Regulation Compliance-Assistance. By S. Kerrigan, and K. H. Law. Submitted to the Ninth International Conference on Artificial Intelligence and Law (ICAIL 2003), June 24-28, 2003, Edinburgh, Scotland, UK, 2003.
• Building a digital lawyer? Stanford/EPA research project experiments with computerizing legal interpretation. By Gale Holland. NSF's Digital Government Online (August 2002).
• NSF researchers present digital solutions to government challenges. NSF Press Release (May 16, 2003).

Second International Workshop on Legal Ontologies; University of Amsterdam, Netherlands. Organised in conjunction with JURIX 2001: the 14th Annual International Conference on Legal Knowledge and Information Systems. Under the heading "Contributions" you'll find links to several papers including: J. Lehmann, Specifying Knowledge for Reasoning about Causation and Assessing Legal Responsibility; and J. Zeleznikow and A. Stranieri, An Ontology for the Construction of Legal Decision Support Systems.

SplitUp: Predicting judges decisions in divorce cases. Developed by Dr Andrew Stranieri and Professor John Zeleznikow at La Trobe University, and Associate Professor John Yearwood at the University of Ballarat. "What is Split Up ? Split Up is a computer program that uses advances in artificial intelligence to decide how much of the property of a marriage would be awarded to the husband and how much to the wife by a judge if the matter was litigated in the Family Court of Australia We hope that Split Up may ultimately be used to give people an idea about what might happen in Court. This may help couples negotiate a property settlement out of Court saving heartache and money. ... Split Up: Underlying motivation: We believe that information technology can make a positive contribution to a just society by encourage reasoning to be structured in a transparent way. This does not mean that we develop systems that replace judicial discretion with rigid formulaic frameworks. Rather, we believe that discretion so important to many just outcomes can be preserved with the application of artificial intelligence to model the way in which arguments are structured. We call this structured reasoning and have developed programs called webShell and ArgumentDeveloper to implement structured reasoning in any field."

• Also see: Family Winner. By Emilia Bellucci and John Zeleznikow. The New Inventors program on ABC-TV (November 16, 2005). "Family Winner is a conflict resolution software package that assists divorcees to rationally negotiate their disputes. It does this by advising rational options for trade-offs of assets, between the opposing parties." [Video available.]
• March of the robolawyers. The Economist Technology Quarterly (March 9, 2006; subscription req'd). "[T]he system, called Family Winner, guides the couple through a series of trade-offs and compensation strategies. According to John Zeleznikow, a computer scientist at Victoria University in Melbourne, who developed the software with his colleague Emilia Bellucci, the results are fairer because both parties end up with what they value most. …. This is not Dr Zeleznikow's first venture into the field of robolawyer software. Indeed, for those determined to take their former spouses for everything they've got, he has already developed a different program, called SplitUp, which can encourage them to reconsider mediation."

UKcorporator®, Interactive Online Company Formation, "uses an intelligent interview process to tailor the necessary documents for you." A paper about this expert system was presented at the Legal Knowledge Systems in Action - Practical AI in Today's Law Offices workshop held at the Eighth International Conference on Artificial Intelligence and Law (ICAIL 2001).

Other References Offline

Buchanan, Bruce and Thomas E. Headrick. Some Speculation About Artificial Intelligence and Legal Reasoning. 23 Stanford Law Review 40 - 62 (1970).

Daniels, Jody J. and Edwina L. Rissland. A case-based approach to intelligent information retrieval. In Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval (1995; pages 238 - 245).

Clancy, Paul, Gerald Hoenig, and Arnold Schmitt. 1989. An Expert System for Legal Consultation. In Proceedings of the Second Annual Conference on Innovative Applications of Artificial Intelligence, 125 - 135. Menlo Park, Calif.: AAAI Press. "This paper describes an expert system that was developed to assist attorneys and paralegals in the closing process for commercial real estate mortgage loans. The system identifies the legal requirements for closing the loans by considering the numerous individual features specific to each particular loan. It was felt that an expert system could provide significant benefits to this process, which is extremely complex and involves large amounts of money. To our knowledge, expert systems technology had not previously been applied to this domain. Successful development and implementation of the system resulted in the realization of the anticipated benefits, and a few others as well."

Costa, Marco, Orlando Sousa, and José Neves. 1999. Legal Knowledge Management. In Exploring Synergies of Knowledge Management and Case-Based Reasoning: Papers from the 1999 AAAI Workshop, ed. David Aha, Irma Becerra-Fernandez, Frank Maurer, and Hector Munoz-Avila, 19 - . Technical Report WS-99-10. American Association for Artificial Intelligence, Menlo Park, California. Abstract: "Knowledge in the legal domain assumes two distinct forms: case law and legislation. Case law complements legislation, and refers to the use of cases decided in court to provide interpretations to subjective aspects of the legislation. These cases are used as guidance in future similar cases. This paper presents a Case-Based Reasoning (CBR) system that establishes legal case-bases, allowing the users to find and retrieve information on cases similar to current ones."

Gardner, Anne von der Lieth. 1987. An Artificial Intelligence Approach to Legal Reasoning. Cambridge, MA: MIT Press.

Gordon, Thomas F. 1995. The Pleadings Game : An Artificial Intelligence Model of Procedural Justice. Boston: Kluwer Academic Publishers.

Gray, Pamela N. 1997. Artificial Legal Intelligence. Brookfield, VT: Dartmouth.

McCarty, L.Thorne., Reflections on Taxman: An Experiment in Artificial Intelligence and Legal Reasoning, 90 Harvard Law Review 837 (1977).

Nagel, Rebecca Thompson. June/July 1998. HAL, Esq. - Will computers someday replace attorneys in the delivery of legal services? We profile one woman whose work with artificial intelligence could forecast the future of the profession. Law Office Computing (subscription req'd.). "A computer that can think like an attorney? Artificial intelligence in a real-life application? Science fiction, right? Well, a system like the one described above is not yet available...commercially. But it does exist in the laboratory of University of Massachusetts, Amherst professor Dr. Edwina Rissland. ... The key to these programs is case-based reasoning (CBR) -- a subsection of AI that uses examples and analogy, as opposed to rules or logic, to solve problems."

Rissland, Edwina L. AI and Similarity. IEEE Intelligent Systems (May/June 2006) 21(3): 39-49.

Rissland, Edwina L. Artificial Intelligence and Law: Stepping Stones to a Model of Legal Reasoning. 99 Yale Law Journal 1957-1981 (1990).

Sartor, Giovanni 1993. Artificial Intelligence and Law : Legal Philosophy and Legal Theory. Oslo: Tano.

Susskind, Richard. 1993. Essays on Law and Artificial Intelligence. Oslo: Tano.

Valente, A. editor. 1995. Legal Knowledge Engineering A Modelling Approach. Volume 30, Frontiers in Artificial Intelligence and Applications. The Netherlands, IOS Press.

Wahlgren, Peter. 1992. Automation of Legal Reasoning : A Study on Artificial Intelligence and Law. Boston: Kluwer.

Zeleznikow, John and Dan Hunter. 1994. Building Intelligent Legal Information Systems: Representation and Reasoning in Law. Deventer: Kluwer. ISBN 90 6544 8330.