June 27, 2019 @ 11:30 am EDT

 

Up to 80% of enterprise information is unstructured—it is information or ‘data’ in the form of presentation files, emails and documents. Not only does unstructured data represent a large proportion of enterprise data today, it is also growing faster than structured data.

Enterprises are struggling to locate relevant information in their unstructured data sources and to connect structured data and unstructured content. Enriching and categorizing content using terms from curated, controlled vocabularies, makes it more findable. It also creates a foundation for linking structured and unstructured sources based on the common terms. Given the large amounts of unstructured data, this processing should be as automated as possible.

TopBraid Tagger and AutoClassifier uses state-of-the art Machine Learning to automatically assign most relevant tags and to further enrich the content.  It takes advantage of ML being controlled by vocabularies and humans in the loop to rapidly refine training sets and initial tag suggestions.

Who Should Attend:

  • Current users of TopBraid EDG
  • Anyone considering the improvement of your search, navigation and lifecycle management of your content vocabulary.
  • Taxonomists, vocabulary managers, content curators and content librarians who are enhancing documents with taxonomy concepts
  • Content and information creators looking for deeper insights into their information
The webinar content will span end user capabilities as well as some of the more technical capabilities, making it appropriate for a broad range of information stakeholders.

In this webinar we will address various scenarios of Autoclassification that depend on your goals as illustrated by the following questions:

  • Do you already have a search engine and want to make it more intelligent?
  • Do you need an intelligent search engine based on managed vocabularies?
  • Do you need a real-time autoclassification service?

About the Presenters:

Jesse Lambert

Jesse Lambert is a Semantic Solutions Architect at TopQuadrant and has over a decade of experience in applying Semantic Web technologies. He is currently supporting a large, public financial institution with their integration of TopBraid EDG into a semantic search pipeline that enables business users and eliminates data stovepipes.

Nuno Lopes

Nuno is a Senior Semantic Solutions Architect at TopQuadrant. His work focuses on applying semantic standards, deploying and customizing TopQuadrantproducts working in different client projects mostly in the biomedical and life sciences domains. Nuno has over 10 years of experience in Research and Development and, prior to joining TopQuadrant, he worked as a Research Engineer at the Smarter Cities Technology Centre, IBM Research, Dublin and a Postdoctoral Researcher (Research Associate) with the Digital Enterprise Research Institute (DERI).