ARCHIVED CONTENT
You are viewing ARCHIVED CONTENT released online between 1 April 2010 and 24 August 2018 or content that has been selectively archived and is no longer active. Content in this archive is NOT UPDATED, and links may not function.By Lexbe
http://www.complexdiscovery.com/info/wp-content/uploads/2015/04/Lexbe-Assisted-Review-.pdf
Lexbe provides eDiscovery software and services for legal professionals at law firms, corporations, and government agencies.
In this white paper, Lexbe describes its newly released technology assisted review (Assisted Review+) offering and compares it against the results of four predictive coding or computer assisted review services/algorithms through the lens of the 2009 TREC study.
Technology assisted review (TAR) also called predictive coding, computer assisted review (CAR), and other names has in recent years been used to allow computer based review of large document sets for production, with human reviewers only reviewing and coding relatively small seed and quality control sets to train and check the computer. As noted by the ABA Section on Litigation: “Technology has created a problem [by building] an overwhelming volume of data that is exponentially more expensive to deal with in litigation” and potentially “technology [can] solve the problem that technology created”. That’s the promise of Technology Assisted Review. With TAR, a skilled reviewer can train a computer to code an entire set of documents from a relatively small training set.
Lexbe’s technology assisted review (Assisted Review+) allows cases with millions of documents and tens of millions of pages to be reviewed for production with expert human reviewers coding only about 5,000 documents, split between a seed set and a control set. Lexbe’s Assisted Review+ is based on a ‘Bayesian Classifier ’, a well known and accepted classification algorithm that can be effectively applied to large predictive coding tasks. Lexbe’s transparent approach is in stark contrast to the ‘black box’ approach of many other eDiscovery service providers that don’t disclose the exact algorithm used to generate computer assisted review results. With ‘black box’ methodologies, the production of responsive documents, and the withholding of non-responsive documents, is done by a secret algorithm that cannot be tested or reviewed for accuracy or completeness. We prefer instead and implement a transparent approach to this important application of computer power to the discovery process.
Click here for a direct link to a complete PDF of the White Paper.