REX is designed for integration into software systems for information retrieval, content/knowledge management, data warehousing, business intelligence, and other information-intensive applications. It uses advanced linguistics to help these systems classify, manage, analyze, and mine large amounts of unstructured text coming from such sources as email, document files, and the Web.
REX helps prepare text for deeper analysis by identifying entities such as: Names, Places, Organizations, Noun Phrases, and Dates. REX also tags an entity's part-of-speech (such as noun, adverb, etc.) and detects sentence boundaries. REX is available immediately for English, German, and Japanese, with additional languages to be introduced later this year.
The company also introduced several new additions to its family of Rosette Language Analyzers, offering linguistic analysis of European languages including English, French, Italian, German, and Spanish. The analyzers are based on linguistic, as opposed to purely statistical, algorithms and rely on code that is unique to each particular language.