|Thursday, October 15th @ 11:00 EDT|
Deep Dives into TopBraid EVN — Part 1: Automated tagging with the New AutoClassifier
Add value to your content with machine learning technology
Special Note: This is the first in a series of 30 minute ‘deep dive’ webinars on TopBraid Enterprise Vocabulary Net (EVN) that will feature short demos on some key capabilities provided by EVN 5.0. Subsequent webinars will cover topics such as collaborative ontology management and change management and evolution.
When your content has keyword metadata assigned to it, it becomes more valuable because your customers and employees can find it more easily. With the release of TopBraid EVN 5.0, the new AutoClassifier uses advanced machine learning technology to automatically tag content with terms from your controlled vocabularies. The ability to automate this tag assignment lets you scale up much further in how your controlled vocabularies enhance the value of your content. For more details on the AutoClassifier see Richard’s latest blog post: Automated Tagging with the new AutoClassifier.
For several years, TopBraid EVN's Tagger has let users take terms from taxonomies and thesauri curated with TopBraid EVN and manually assign those terms to their content so that their co-workers and customers could more easily find and use that content. As with manual content tagging, the tag sets created by AutoClassifier take full advantage of TopBraid EVN's advanced governance, workflow and collaboration features.
Who Should Attend: Digital Asset Managers, Taxonomists, Publishers, Metadata Specialists, Content Managers, Information Architects and anyone who works with taxonomies, thesauri, ontologies, and other controlled vocabularies as well as the content used with these vocabularies.
Join us to learn how TopBraid EVN AutoClassifier can provide your organization with these benefits:
- Reduced time spent on reviewing textual documents for their classification
- An automated yet auditable system where humans can validate or reject auto-classification results
- Ability to effectively process growing amounts of content and to reduce the associated risks and costs
- Reduced costs in the design of complementary information retrieval systems, such as faceted search engines
More on the Speakers:
Richard Cyganiak is a Principle Software Engineer at TopQuadrant and developer of TopBraid EVN Tagger’s AutoClassifier capability. Through his career, Richard has been a Semantic Web thought leader, researcher and evangelist with a strong software development background. He continues this ‘Web of Data’ interest as maintainer of several open-source software projects in the Semantic Web and RDF area. His special focus and capabilities include database-to-RDF mapping, RDF publishing, Linked Data, Web crawling, legacy data conversion and Java programming.
Prior to joining TopQuadrant Richard was a Linked Data researcher at Insight Centre for Data Analytics (DERI) where he led development teams and managed academic research and software commercialization projects. He also performed extensive technical writing, maintaining software documentation, editing specifications for standards groups, and blogging on technical subjects
In addition to his research and development positions, for many years Richard has been involved in OpenSource Community building. He has made key contributions as a developer of D2R, the leading SPARQL-to-SQL engine, and in many Linked Data projects including Dbpedia.
Bob DuCharme is a Senior Semantic Solutions Architect at TopQuadrant. He performs solution requirements, architecture analysis, design, and semantic model-driven application development on TopBraid EVN and the TopBraid platform, especially in the area of custom and standardized controlled vocabularies and the relationships between these. Bob came to TopQuadrant in 2009 from Innodata Isogen, where he did system and architecture analysis and design for a wide range of global publishing clients as well as co-chairing the 2008 Linked Data Planet conference in New York City. Earlier in his career, he oversaw SGML and XML development at Moody's Investors Service and then moved on to LexisNexis, where he did data and systems architecture as they made the transition to XML-based systems.
He is the author of O’Reilly’s “Learning SPARQL,” the only book devoted to the Semantic Web query language. Bob’s other books include Manning Publications' “XSLT Quickly,” Prentice Hall's “XML: The Annotated Specification,” and McGraw Hill's “Operating Systems Handbook.”
A Principle Software Engineer at TopQuadrant, Richard is the developer of TopBraid EVN Tagger’s AutoClassifier capability. Richard will give an overview of the importance and challenges associated with autoclassification. He will highlight ways in which powerful machine learning methodologies have been utilized to enable faster, richer content tagging.