No text analysis engine is best-of-breed for all knowledge domains and all languages, and integration with more specialized text analysis tools is often more appropriate to meet specific industry or application needs. In order to facilitate integration with these tools, Mark Logic has created the Open Enrichment Framework. The Open Enrichment Framework lets Mark Logic customers choose the entity enrichment engine that best suits their needs by providing an easy-to-use API for integration of text analysis products.

MarkLogic Server’s built-in entity enrichment functionality provides general-purpose text analysis suitable for many knowledge domains and the most popular languages. It automatically identifies entities and performs inline markup of the content, allowing for easier and more powerful exploitation of information.

Several Mark Logic technology partners have used the Open Enrichment Framework to create pre-built pipelines, which provide simplified out-of-the-box integration with their products. This means that customers can immediately begin using the two products together to mark up content stored in MarkLogic Server based on the enrichment tool of their choice.

A Mark Logic customer that has already installed any of the products listed below will be able to click a few buttons in the MarkLogic Server administration interface and have all of its documents (or all documents in a specified directory) enriched using the chosen third-party product. Mark Logic will be making “pipelines” available for each Open Enrichment Framework member and product.

For more information regarding the Open Enrichment Framework, please contact .

	TEMIS’ Luxid® provides domain-specific data enrichment services to over 200 customers in a wide range of industries, including: Life Sciences , Publishing & Media, Financial Services, Homeland Security, Utilities & Energy and Telecoms. Luxid® creates an enriched XML that contains semantic entities, concepts and relationships, enabling richer XQueries and facets in Mark Logic Server-based applications. Luxid® uses a library of pre-built annotators, the Skill Cartridge™ Library that can be easily customized to fit the exact needs of your business. For more information: www.temis.com.
	The Access Innovation's OEF plug-in provides full entity extraction and meta tagging inline in the XML document.  It guides the eye directly to the location of the source data while insuring high precision and recall in the search.  Using Data Harmony MAIstro on the source data structures it to the full expanse of the taxonomy and the client schema automatically.  Try it out at www.dataharmony.com/marklogic
	Janya is a language technology company that provides products and services to support information discovery from unstructured and semi-structured data. With more than a decade of experience developing and integrating this technology, Janya works closely with customers to incorporate information discovery capability in a variety of environments and workflows. Janya’s solutions provide extensive extraction capabilities that go beyond just entities to include events and complex relationships, in a flexible distributed architecture that is suitable for both low and high volume environments.
	NetOwl® supports the Mark Logic Open Enrichment Framework (OEF) in the most optimal fashion through its built-in in-line XML output.  NetOwl's flexible Services API allows the highly scalable NetOwl server to plug directly into the OEF.  NetOwl enriches unstructured data content dramatically by extracting key concepts – including entities, links, and events – as defined in its semantic ontology, which is the most extensive available on the market. NetOwl also offers state-of-the-art geo-tagging capabilities to “geo-enable” texts for advanced geospatial analysis.  Additionally, NetOwl supports multiple foreign languages, such as Arabic and Chinese, and provides name translation and name matching capabilities to make foreign language data more accessible.