Xerox Introduces Fast and Effective Foreign Language Detection to Expedite Global E-Discovery Projects

New e-discovery feature sorts documents by language(s) at the sentence level, making legal review faster and more cost-effective

Xerox launched a new e-discovery tool to accelerate review by quickly sorting documents based on their language(s). Xerox Litigation Services’ Foreign Language Identifier detects more than 45 languages, allowing for faster and more efficient discovery on global litigation matters.

Developed by researchers at the Xerox Research Centre Europe (XRCE), Foreign Language Identifier instantly determines which languages a document contains; it identifies the majority language and all others present and provides a percentage breakdown of each. Unlike other foreign language detection tools, Xerox’s Foreign Language Identifier can parse language at the sentence level as opposed to the document level, and is therefore able to identify multiple languages in a document more accurately than a standard foreign language identifier that only considers the majority language. This is critical in increasingly global, complex litigation matters.

“As companies and litigation become more global, attorneys find themselves sorting through mass quantities of documents with multiple languages during discovery,” said Craig Freeman, senior vice president, Xerox Litigation Services. “Foreign Language Identifier streamlines the review process by giving lawyers instant intelligence regarding the languages used and in which documents these languages appear.”

Xerox Litigation Services’ Foreign Language Identifier, allows attorneys to understand the foreign language requirements of a matter earlier in the discovery process and to anticipate and assemble the review workflow and the translation services required. For instance, if a case involves data in both French and Spanish, an attorney can ensure there are resources to manage such data in a timely manner. Traditional language detection tools would only identify the predominant language appearing in each document, e.g. the French data ; resources to manage the Spanish data would need to be enlisted later in the process, likely causing additional cost as well as review and production delays.

Xerox developed its Foreign Language Identifier at the renowned XRCE research facility in Grenoble, France; this makes Xerox unique in the e-discovery space for having developed proprietary foreign language software that detects languages at the sentence level. Foreign Language Identifier is the latest enhancement to the Xerox Litigation Services e-discovery platform and is supported by other analytical tools such as E-Mail Analytics and near duplication detection software. These proprietary technologies are accessible from each client’s custom Web site for no additional charge.