Embedded Text Mining

Eliminate tagging headaches

Automatic discovery & extraction of meaning is key to finding and packaging assets, with metadata becoming a key part of an asset. Nstein's DAM 4 natively showcases Nstein's powerful TME (Text Mining Engine) to help enrich, organize and understand large quantities of content.

Traditional tagging requires editors to do a complex and repetitive task that they often don't have time to do. Automatic discovery and extraction of meaning provides the only consistent means to comprehensively and accurately tag content in a consistent manner.

Discover content's unique semantic footprint

Nstein TME automatically extracts concepts, proper names, organization names and geographical locations stored in your content based on machine learning and your authority files. This "semantic footprint" becomes the foundation for better reuse and understanding of content while simultaneosly making it ready for the semantic Web.

True asset enrichment

All of the metadata provided via Nstein's semantic enrichment process become permanent features of the asset. Can a Web CMS use a list of people mentioned in a news item? This metadata can be easily exported as a key part of the asset.

Out-of-the-box IPTC categorization

Nstein's WCM 4 provides categorization based on industry-specific IPTC taxonomies - and support for custom taxonomies. Based on linguistic analysis, the system automatically categorizes content with the appropriate taxonomy nodes. Archivists maintain the ability to verify, modify or delete all the metadata created automatically.