Digital White Papers

I L T A W H I T E P A P E R & S U R V E Y R E S U L T S | L I T I G A T I O N A N D P R A C T I C E S U P P O R T & C O R P O R A T E L E G A L D E P A R T M E N T S 32 documents earlier than in either TAR 1.0 or TAR 2.0 approaches. In the case of low-richness scenarios, this last item gives TAR 3.0 an advantage over earlier versions. Pairing early access to responsive documents with valid yield estimation is crucial to understanding when review is complete when the prevalence of responsive content is low. TAR 3.0 can achieve superior results over TAR 2.0, particularly for teams facing issues with low richness, or those under pressure to accelerate review timelines while retaining high levels of accuracy. When considering a TAR 3.0 solution, ask providers about techniques for boosting active learning: Do they have an approach that offers curated samples that ensure a diverse set of documents is presented to a model alongside documents that are likely to be responsive? Do they generate yield estimates to enable informed decisions about review completion? TAR 3.0 should offer new opportunities for discovery technologists and practitioners to derive greater value and results, gains that stem from a heightened focus on outcomes and quality over cosmetic software features. Just Do It Technology-assisted review has come a long way since predictive coding. The range of solutions has grown, and each has the potential to add value. While the factors outlined above should be considered in determining which version of TAR to employ for any given instance, don't spend so much time researching and testing options that you lose valuable time and progress in the process. Legal teams often are reluctant to try a new method or approach until they have clear evidence of its value. But in the case of document review, the best way to determine which TAR version will be the best fit is to simply start using it. The impact of learning later that one version wasn't the perfect choice may be far less than the impact of time lost in not using any technology to assist in the review. And the more you employ any option, the more experience you'll gain and the easier it will be to make an informed decision for future matters. ILTA Dr. Gina Taranto is the Director of Applied Sciences at Prosearch and leads research and innovation of accelerated learning solutions by directing multidisciplinary teams of technologists, subject matter experts and data scientists to train the technologies that replicate human decisions. She built the original ProSearch Linguistics, Analytics, and Data Science group and oversees the design and implementation of search and automated document review solutions. She is recognized for her expertise in the range of technology-assisted review technologies, including the application of TAR to emerging issues in protecting private information. She is a published author in the fields of linguistics and information retrieval. Previously, Dr. Taranto was a lead linguist and adviser to client engagements at H5, and a research linguist at both A-Life Medical, Inc. and Northrop Grumman Information Systems. She received her B.A. with honors from Kresge College at the University of California, and her M.A. and Ph.D. from the University of California, San Diego. L I S T E N I N A S W E C O N T I N U E T H E C O N V E R S A T I O N P O D C A S T C O M I N G S O O N !

• Cover