Tutorial Organizer: Ontotext
This tutorial covers a broad range of advantages that Semantic Technology offers such as the integration of dynamic data from virtually unlimited sources, flexible data modeling, automated knowledge discovery, and interlinking with Linked Open Data (LOD).
Some of these techniques will be demonstrated through a specific use case in which raw textual data will be transformed into RDF with the help of GraphDB, Ontotext’s industry-leading RDF triplestore. Then, with the help of LOD we will link these resources and will enable complex querying of data from both sources.
We shall also demonstrate in-house technologies for building semantic applications based on robust text analysis techniques, again benefiting from LOD. We will share knowledge and insights from our experience which includes developing NLP pipelines for numerous domains and languages - academic & scientific publishing, healthcare, pharmaceutical, cultural heritage; English, German, Dutch, French, Italian, and Chinese.
As part of this tutorial we will demonstrate two use cases that leverage Linked Open Data.
This tutorial is a modified version of Ontotext's successful course <https://ontotext.com/designing-semtech-poc/> tailored to teach people how to build a small Proof-of-Concept project that utilized the power of Semantic Technology.
This tutorial is free of charge for conference attendees.
- Semantic Technologies - the Ontotext Way
- Loading/Transforming/Modifying data in GraphDB – a practical session with OntoRefine
- A Demonstration of Leveraging LOD for Linking Diverse Data Sources – a practical session with SPARQL and linking data
- LOD Vocabulary Management for Robust Text Analysis and Semantic Search
A basic understanding of Semantic Technology and some programming skills, SPARQL in particular, would greatly benefit towards the experience of this tutorial.
In addition, participants are encouraged to bring a computer to be able to evaluate the database themselves. Although this will be a lecture-oriented tutorial, some of the data used in the examples will be provided and participants will be provided with an opportunity to perform certain demonstration tasks.
- Plamen Tarkalanov, Semantic Data Integration Consultant*
As Semantic Data Integration Consultant, Planen is primarily responsible for ETL of various sources to RDF. Mappings, entity matching and process automation are among his secondary responsibilities. He has also experience in the Marketing Research industry as data processing specialist.
- Ivelina Nikolova, PhD. NLP Engineer
Ivelina has over 10 years of experience in natural language processing. Recently she has been focusing on the application of NLP techniques for enhancing semantic technologies, which is also the topic of her Ph.D. thesis. Her expertise in semantic annotation and information extraction is the result of numerous research and commercial projects in domains like news & media, financial, biomedical and cultural heritage. In these areas, she sets to solve problems related to named entity recognition, relation extraction, and event modeling.
Ontotext is a Semantic Technology company based in Bulgaria.
We transform the way enterprises identify meaning across diverse databases and unstructured data, by combining text mining and machine learning techniques with a fully developed semantic graph database, GraphDB.
We develop cutting-edge technology products and solutions based on cognitive computing, machine learning, natural language processing, noSQL databases.
Our challenge is to make these complex technologies easier to adopt and use at scale for data-intensive companies. Some of the global enterprise players who have already trusted our technology are BBC, the Financial Times, Springer Nature, AstraZeneca and BabylonHealth.
For this workshop Ontotext provides free tickets.
This offer is limited to 20 tickets and given on a fist-come, first-serve basis.
Get your free ticket here, and come back for registration later.