Peer to Peer Magazine

P E E R T O P E E R : I L T A ' S Q U A R T E R L Y M A G A Z I N E | S U M M E R 2 0 1 9 55 rather than the image itself. Characteristics such as color count, color range, EXIF (exchangeable image file) format, GPS location, image size and skin tone are used to represent an image. Using that data, eDiscovery tools can locate desired images, or at least significantly reduce the population of images for potential consideration. Moving beyond metadata to evaluate images on the visual characteristics of the image alone is the next step in image recognition. There are available visual classification tools that can group images into various categories, such as people, indoor scenes, outdoor scenes, automobiles and airplanes. As with NLP, those top level visual assessments can be used as features with a technolo-assisted review algorithm to recognize the characteristics that may make an image responsive, and potentially responsive images can be elevated for review. And those visual classification tools can be trained to encompass even more categories, and make even finer distinctions. However, as with NLP, it will take time to fully test and develop the feature set that can be generated through visual analysis, and train the visual classification tools to make the proper distinctions – particularly for specific litigations. Conclusion To a limited extent, artificial intelligence in the form of natural language processing and image recognition is being used in eDiscovery today. Extracting NLP and image features for use with technolo-assisted review tools certainly provides a level of efficiency that would otherwise be unavailable. And there is certainly movement in the direction of exploiting both techniques even further. However, the ultimate utility of both NLP and image recognition techniques must await careful consideration, thorough testing, comprehensive training… and time. ILTA . 1 https://catalystsecure.com/pdfs/Effectiveness%20Results%20for%20 Popular%20e-Discovery%20Algorithms.pdf Thomas C. Gricks III A prominent e-discovery lawyer and a leading authority on the use of technolo-assisted review, Tom is the Director of Data Analytics at OpenText. At Catalyst he advised corporations and law firms on best practices for applying technolo to reduce the time and cost of discovery and investigations. Tom has more than 25 years' experience as a trial lawyer and in-house counsel, most recently with the law firm Schnader Harrison Segal & Lewis, where he was a partner and chair of the E-Discovery Practice Group. He was lead e-discovery counsel in Global Aerospace v. Landow Aviation, the first case in the country to authorize the use of TAR over the objection of opposing counsel. Andrew Bye Andrew is a machine learning solutions consultant at OpenText and a search and information retrieval expert. Throughout his career, Andrew has developed search practices for e-discovery and has worked closely with clients to implement effective workflows from data delivery through statistical validation. Before joining Catalyst, Andrew was a data scientist at Recommind. He has also worked as an independent data consultant and a linguist at H5. Andrew has a bachelor's degree in linguistics from the University of California, Berkeley and a master's in linguistics from UCLA. Jeremy Pickens, Ph.D. Jeremy Pickens is one of the world's leading information retrieval scientists and a pioneer in the field of collaborative exploratory search, a form of information seeking in which a group of people who share a common information need actively collaborate to achieve it. Dr. Pickens has seven patents and patents pending in the field of search and information retrieval. Before joining OpenText, Dr. Pickens spearheaded the development of Insight Predict at Catalyst. His ongoing research and development focuses on methods for continuous learning, and the variety of real world technolo assisted review workflows that are only possible with this approach. Dr. Pickens earned his doctoral degree at the University of Massachusetts, Amherst, Center for Intelligent Information Retrieval. He conducted his post- doctoral work at King's College, London. In addition to his OpenText responsibilities, he continues to organize research workshops and speak at scientific conferences around the world.

• Cover