Lu and Conrad on Bringing Order to Legal Documents: An Issue-based Recommendation System via Cluster Association

Qiang Lu and Jack G. Conrad, both of Thomson Reuters, will present a paper entitled Bringing Order to Legal Documents: An Issue-based Recommendation System via Cluster Association, at KEOD 2012: The 4th International Conference on Knowledge Engineering and Ontology Development, to be held 4-7 October 2012 in Barcelona, Catalonia, Spain.

Here is the abstract:

The task of recommending content to professionals (such as attorneys or brokers) differs greatly from the task of recommending news to casual readers. A casual reader may be satisfied with a couple of good recommendations, whereas an attorney will demand precise and comprehensive recommendations from various content sources when conducting legal research. Legal documents are intrinsically complex and multi-topical, contain carefully crafted, professional, domain-specific language, and possess a broad and unevenly distributed coverage of issues. Consequently, a high quality content recommendation system for legal documents requires the ability to detect significant topics from a document and recommend high quality content accordingly. Moreover, a litigation attorney preparing for a case needs to be thoroughly familiar the principal arguments associated with various supporting opinions, but also with the secondary and tertiary arguments as well. This paper introduces an issue-based content recommendation system with a built-in topic detection/segmentation algorithm for the legal domain. The system leverages existing legal document metadata such as topical classifications, document citations, and click stream data from user behavior databases, to produce an accurate topic detection algorithm. It then links each individual topic to a comprehensive pre-defined topic (cluster) repository via an association process. A cluster labeling algorithm is designed and applied to provide a precise, meaningful label for each of the clusters in the repository, where each cluster is also populated with member documents from across different content types. This system has been applied successfully to very large collections of legal documents, O(100M), which include judicial opinions, statutes, regulations, court briefs, and analytical documents. Extensive evaluations were conducted to determine the efficiency and effectiveness of the algorithms in topic detection, cluster association, and cluster labeling. Subsequent evaluations conducted by legal domain experts have demonstrated that the quality of the resulting recommendations across different content types is close to those created by human experts.

For full text of the paper, please contact the authors.

Thanks to Jack for allowing me to post the abstract.

Justiss on A Survey of Electronic Research Alternatives to Lexis and Westlaw in Law Firms

Laura K. Justiss of Southern Methodist University School of Law Library has posted a working paper entitled A Survey of Electronic Research Alternatives to Lexis and Westlaw in Law Firms, on SSRN. Here is the abstract:

Mrs. Justiss conducted a survey of law firm librarians in 2010 that identified electronic research database alternatives to Lexis and Westlaw and ranked them by subscription frequency. The survey included research databases for primary source alternatives; court docket and case information services; secondary sources for topical legal research and legal periodicals; financial, business and news sources; public records; and non-legal and legal-related sources, including intellectual property databases. The survey also generated information regarding suggested or mandated legal research policies in law firms for the use of alternatives to Lexis and Westlaw and examined their applicability to billable and non-billable research. Lastly, it examined the prevalence in firms of flat rate pricing agreements with Lexis, Westlaw or both.

HT Martha Sperry and @uMCLE.

Jackson on WestlawNext and the State of the Art in Legal Information Systems

Dr. Peter Jackson, Chief Scientist and Vice President of Technology at Thomson Reuters, discusses the new WestlawNext computer-assisted legal research system, and the current state of the art in legal information systems, in a very interesting interview with Jason Wilson of Jones McClure, published today on Slaw, the Canadian legal blog.

Nevelov Mart, A Study of West’s Headnotes and Key Numbers and LexisNexis’s Headnotes and Topics

Susan Nevelow Mart of the University of California Hastings College of Law has published The Relevance of Results Generated by Human Indexing and Computer Algorithms: A Study of West’s Headnotes and Key Numbers and LexisNexis’s Headnotes and Topics, 102 Law Library Journal No. 2, pages 221-249 (2010). Here is the abstract:

This article begins the investigation into the different ways results are generated in West’s “Custom Digest” and in LexisNexis’s “Search by Topic or Headnote” and by KeyCite and Shepard’s. The author took ten pairs of matching headnotes from important federal and California cases and reviewed the results sets generated by each classification and citator system for relevance. The differences in the results sets for classification systems and for citator systems raise interesting issues about the efficiency and comprehensiveness of any one system, and the need to adjust research strategies accordingly.

New Westlaw, Lexis, Bloomberg Systems Previewed by ABA Journal

[NOTE: Updated on 31 January 2010 to clarify the statement in the article that "[s]econdary sources will be coming soon to Fastcase.”]

New and revamped online legal research systems offered by Westlaw, Lexis.com, and Bloomberg are previewed in an article published online today by ABA Journal. Fastcase and Google Scholar are also discussed in the article.

Among the novel features of the new systems to be offered by Westlaw, Lexis, and Bloomberg, the article identifies simplified user interfaces, improved natural language searching, better organized results displays, graphical displays of some data including citator results, and artificial intelligence features, including decision support.

The article also states that Fastcase plans to add secondary sources to its databases in the coming year. However, according to Ed Walters, CEO of Fastcase, Fastcase’s content already includes secondary sources, including “newspapers, a people finder, business intelligence, and forms.” Walters says that additional secondary sources will be added to Fastcase in the future.

Google Scholar personnel are quoted in the article as stating that they have no plans to add significant improvements to the legal research components of their system.

Overall, the article appears to reflect a distinctly more competitive market for online legal research in the U. S.

Debate on Free Access to Law

[NOTE: Updated on 10 November 2010 to link to Professor Bruce's post entitled More West: What Legal Information Business Should The Government Be Out Of?. Updated on 8 November 2009 to link to Professor Bruce's post entitled The West Video and the Free Market. Updated on 4 November 2009 to link to Professor Berring's Nov. 3 reply, on sLaw.]

An interesting debate over free access to law is now occurring in the legal blogosphere.

Thomson Reuters, owners of West Publishing, a major U.S. legal publisher, and the Westlaw computer assisted legal research (CALR) service, recently published video comments about the free access to law movement by Professor Robert Berring of the University of California Berkeley School of Law, and a well respected expert on legal research. In the video Professor Berring praises the free access to law movement for increasing competition in the CALR market and compelling Westlaw and its main rival in the U.S. market, Lexis.com, to innovate. Yet Professor Berring also criticizes the free access to law movement as fleeting, and as providing insufficient metadata to enable high quality legal research.

This week Professor Daniel Poulin, Director of CanLII, the Canadian Legal Information Institute, responded to Professor Berring’s comments, on the sLaw blog, and yesterday Professor Tom Bruce, Director of Cornell’s Legal Information Institute, published his response on his B-Screeds blog.

Ed Walters, Esq., CEO of Fastcase, Inc., has offered to convene a meeting of the participants of this debate.

On November 3, Professor Berring posted a reply, on sLaw.

On November 8, Professor Bruce responded with a post entitled The West Video and the Free Market.

On November 10, Professor Bruce responded again with a post entitled More West: What Legal Information Business Should The Government Be Out Of?.

Those interested in digital legal information or public access to legal information may find this debate particularly informative and timely.

HT @caminick for tweeting Prof. Poulin’s post.

Nevelow Mart on Human Indexing & Computer Algorithms in Case Law Subject Classification

Susan Nevelow Mart, Faculty Services Librarian & Adjunct Professor of Law at the UC Hastings Law Library, has published Reining in the Results: The Use of Human Indexing and Computer Algorithms in West’s Headnotes & Key Numbers and LexisNexis’s Headnotes & Topics as Tools for Finding Relevant Case Law, forthcoming in Law Library Journal. An earlier version of the paper was presented at the Conference on Legal Information: Scholarship and Teaching, held at the University of Colorado Law School on June 21-22, 2009, as part of its Boulder Summer Conference Series. Here is the abstract:

“Since the advent of LexisNexis headnotes and the LexisNexis classification system, the author has wondered about the different ways results are generated in West’s Custom Digest and in LexisNexis’s ‘Search by Topic or Headnote’ and by KeyCite and Shepard’s. There has been some anecdotal discussion about the differences, but no empirical investigation. This paper starts the investigation process: the author took ten pairs of matching headnotes from legally important federal and California cases and reviewed the cases in the results sets generated by each classification and citator system for relevance. The relevance standards for each case are included. The paper first reviews previous full-text database testing, and the benefits and detriments of both human indexing and algorithmic indexing. Then the two very different systems are tested. Ten pairs of headnotes is too small a sample to say absolutely that results generated by system A are and always will be a certain percentage more or less relevant than system B. However, the differences in the results sets for classification systems and for citator systems do raise some interesting issues about the efficiency and comprehensiveness of any one system, and the need to adjust research strategies accordingly.”

Lomio on the History of CALR

Prof. Paul Lomio has an intriguing account of the origins of computer-assisted legal research services, with attention to antitrust issues.