ZyLAB claims its integration of text analytics into its eDiscovery & Production System will help make Early Case Assessments (ECA) more efficient and less costly.

Text analytics enable organizations to identify, classify, and sort relevant enterprise information prior to initiating the formal Electronic Discovery Reference Model (EDRM) Collection process and extract entities, facts, relationships, concepts and subtext that will influence the litigation strategy. Legal counsel gains greater insight into potential liabilities and can make informed decisions much earlier in the process.

Traditionally, ECA is executed just before the review stage of e-discovery. In order to do this, all data from appointed custodians has to be collected and processed before analysis and review can start. Because ZyLAB’s eDiscovery & Production System is built on a proven information management platform it has the capabilities to analyze information without the need to first collect the data and store it on a collection server. This provides an alternative to waiting for final custodian lists and for their collections to be migrated to the legal hold server for processing. Organizations are saved from potentially unnecessary disruptions and costly collection and processing.

Complementing its various search methodologies (Boolean, wildcard, proximity, and fuzzy searching, but also innovative concept searching), the ZyLAB system integrates text analytics to manage huge volumes of dispersed and unfiltered data. Key capabilities of ZyLAB Text Analytics include:

• Auto-classification and sorting based on the content or file properties
• Extraction of more than 200 types of entities and regular expressions like names, job titles, addresses, and social security numbers
• Extraction of events and facts
• Extraction of unknown concepts, trends and patterns
• Extraction of document and file properties
• Detection and recognition of graphical files (also for OCR of non-OCR-ed bitmaps)
• Detection, recognition and translation of foreign language content, as well as automatic translation of 40 languages
• Detection of exact and near-duplicate files
• Data Visualization to identify patterns, relationships, trends, and connections in dynamic diagrams or even Google Maps.

“We are once again revolutionizing traditional search methodologies, this time to enable organizations to initiate Early Case Assessments sooner and with a better handle on their information,” said Johannes Scholtes, Chief Strategy Officer for ZyLAB. “By focusing on patterns and characteristics our text analytics produce better search results and deeper data analysis, thereby providing quick retrieval of information that otherwise would remain hidden.”

The ZyLAB eDiscovery & Production system is aligned with all critical EDRM phases and addresses all key aspects of e-discovery, from information management to producing relevant data for opposing counsel as well as for use in litigation software. The system offers more advanced third-party product compatible features than any other eDiscovery solution on the market today. It can be completely integrated with other litigation software and common repositories such as Microsoft SharePoint, databases, as well as ECM, CRM and ERP systems. The platform is built around an XML data repository and provides authorized reviewers with access via standard Internet browsers. This helps accelerate case analysis and document review, as well as enables discovery activities to be automatically performed in-house, thereby allowing customers to maintain control and minimize costs.