DESI VI: Exploring Innovation in eDiscovery
The Sixth Workshop on Discovery of Electronically Stored Information (DESI VI) will be held in San Diego on June 8, 2015, as part of the week-long International Conference on Artificial Intelligence and Law (ICAIL). This workshop aims to foster engagement among eDiscovery practitioners and research communities to advance guidelines and standards for machine learning and other advanced eDiscovery techniques as they evolve to address the ever-growing ESI stores that plague litigation, investigation, and information governance efforts.
With the courts showing growing acceptance of advanced techniques for eDiscovery in the name of greater efficiency and efficacy of results, this year’s DESI workshop will aim to broaden the scope of legal issues to which advanced data analysis and classification technologies might credibly be applied, beyond eDiscovery to a fuller range of information governance applications.
Keynote speakers Bennet Borden (Drinker Biddle & Reath LLP) and Jeremy Pickens (Catalyst) will each explore those broader boundaries with the topics “Beyond eDiscovery: Applying Data Analytics to Other Legal Challenges,” and “TAR, Information Governance and the Reativity of Wrong,” respectively.
Driven by a stellar organizing committee that includes Jason R. Baron (Drinker Biddle & Reath LLP), Jack G. Conrad (Thomson Reuters), Amanda Jones (H5), Dave Lewis (David D. Lewis Consulting) and Douglas W. Oard (University of Maryland), the workshop will consider papers that attempt to separate signal from noise in a number of areas related to machine learning, measurement and quality protocols, privacy, and compliance.
H5’s offering, from Amanda Jones, Marzieh Bazrafshan, Fernando Delgado, Tania Lihatsh and Tamara Schuyler, considers The Role of Metadata in Machine Learning for Technology Assisted Review. Access to all of the papers to be presented at DESI VI can be found here.
Questions to be addressed at the DESI VI Workshop include:
- What combinations of machine learning and other techniques can best categorize information in accordance with existing records management policies?
- Do effective methods exist for performing sentiment analysis and personal information identification in a legally useful way in e-mail and other records of interpersonal communication?
- How well can we estimate the end-to-end costs of workflows that combine artificial intelligence and human coding to accomplish legal tasks on a broad range of content types?
- Can proactive insider threat detection leverage information already being collected for records management purposes, and what would be the ethical and legal fallout of such approaches?
- Are approaches available to reduce the perceived conflicts between privilege and transparency in labeling data for Technology-Assisted Review (TAR) in e-discovery and public records access applications?
- What technical, procedural, and legal issues arise from recent proposals to shift the focus of e-discovery from relevance to materiality?
- Where do recent legal cases point to the need for new research to better inform the decision of courts and the practices of parties?
- What lessons can we draw from recent shared-task evaluations such as TREC and EDI, and how can future shared-task evaluations best be structured?
- How can current techniques for issue coding be applied to compliance tasks (e.g., in regulatory, enforcement, and investigations settings), and what capability gaps exist that call for new research?
- What implications do emerging technologies such as deep learning and fine-grained access to behavioral traces have for e-discovery, business intelligence, and records and information management purposes?