Support industrial thesaurus creation with linguistics, statistics and world knowledge: the Luxid WebStudi

Rich, specific and up-to-date vocabularies and thesauri are an important building block for many approaches to the management and analysis of large amounts of textual data. Using thesauri document collections can be enriched with facets, search results can be more targeted and more complete, trends and factual knowledge can be inferred in a better way than on raw text.

But defining and maintaining a large thesaurus on a detailed domain can be a time-consuming and demanding task. Tasks like identifying new potential thesaurus terms or synonyms for these or already existing ones is often exclusively manual work where most existing platform provide little support.

Combining linguistic and statistical evidence with specific world knowledge, the Luxid WebStudio attempts to provide thesaurus managers with this kind of support, embedding the task for thesaurus creation and maintenance in a broad software environment where thesauri can be refined, tested and applied on textual content.

We motivate and introduce the platform and some of the underlying technologies and provide insight into some of the use cases the application has been used for in industry scenarios.

About TEMIS

TEMIS helps organizations structure, manage and leverage their unstructured information assets. Its flagship platform, Luxid®, identifies and extracts targeted information to semantically enrich content with domain-specific metadata. Luxid® enables professional publishers to efficiently package and deliver relevant information to their audience, and helps enterprises to intelligently archive, manage, analyze, discover and share increasing volumes of information.

Based on patented and award-winning natural language processing technology, Luxid® Content Enrichment Platform brings long-awaited answers to the challenge of structuring, managing and exploiting unstructured content. Luxid® is a powerful and scalable solution that recognizes and extracts relevant items of information hidden in plain text. Stored as metadata, these items intimately reveal the nature of your informational assets and help boost the efficiency and scalability of all processes involving the management, distribution, access and analysis of large amounts of textual content.

Claus Blank and Daniel Meyer

Claus has a degree in Computer Science from the University of Applied science in Darmstadt.

He has 15 years successful track record as Sales Manager for enterprise wide complex software solutions with the focus on Information Management, Enterprise Search, E-Discovery & Data Mining.

Since December 2013, he is responsible for the sales activities in Germany, Austria and Switzerland as Sales Director at TEMIS.