Global and Unified Access to Knowledge Graphs

Technologies
python, javascript, scala, rdf, sparql
Topics
data science, natural language processing, data analytics, knowledge graphs, data extraction
Global and Unified Access to Knowledge Graphs

DBpedia extracts structured information from the content created in various Wikimedia projects. This information resembles an open knowledge graph (KG) which is available for everyone on the Web. A KG is a database that stores knowledge in a machine-readable form and provides a means for information to be collected, organised, shared, searched and utilised. The current DBpedia release 2021-01 consists of 21 billion triples (“facts”) and ~750 different “types”. The whole extraction includes 125 languages. It is interlinked to many other databases (e.g., Wikidata). Started in 2006, DBpedia is one of the first open KGs on the Web. Its knowledge base has several advantages over existing ones: it covers many domains; it represents real community agreement; it automatically evolves as Wikipedia changes, and it is truly multilingual. DBpedia provides tools that allow you to create, maintain, improve, integrate and use KGs to build applications, e.g. BBC has created the World Cup 2010 website by interconnecting textual content and facts from their knowledge base. Data provided by DBpedia was greatly involved in creating this knowledge graph. Several other large, medium and small companies use data from DBpedia every day. DBpedia data is served as Linked Data, which is revolutionizing the way applications interact with the Web. One can navigate this Web of facts with standard Web browsers, automated crawlers or pose complex queries with SQL-like query languages (such as SPARQL). Have you thought of asking the Web about all cities with low criminality, warm weather and open jobs? That is the kind of query we are talking about. DBpedia has become a high-impact, high-visibility project because of our foundation in excellent Knowledge Engineering as the pivot point between scientific methods, innovation and industrial-grade output. The drivers behind DBpedia are 6 out of the TOP 10 Most Influential Scholars in Knowledge Engineering and the C-level executives of our members.

2021 Program

Successful Projects

Contributor
Guang Zhang
Mentor
Marvin Hofer, Sebastian Hellmann, Alexander Winter
Organization
DBpedia
Update DBpedia Sparql for newly updated wiki resources and specifically related to pandemic, healthcare, and heath AI fields
IMPACT User-friendly QA platform for a given DBpedia resource and specifically about pandemic in real-time. GOALS To improve the DBpedia Sparql for...
Contributor
Fernando Casabán Blasco
Mentor
Mariano Rico
Organization
DBpedia
Web app to generate RDF from DBpedia abstracts - Fernando Casabán Blasco
With the recent advances in the processing and analysis of texts in natural language, the conversion of texts into RDF triples is becoming a real...
Contributor
Siddhant Jain
Mentor
Tommaso Soru, Anand Panchbhai
Organization
DBpedia
Neural QA Model for DBPedia
In order to make DBpedia and its humongous linked data available to a larger user base in their natural languages, a Neural QA model has been...
Contributor
Ashutosh Kumar-1
Mentor
Edgard Marx, Diego Moussallem, Thiago Castro Ferreira, Nausheen Fatma
Organization
DBpedia
DBpedia Live Neural Question Answering Chatbot - GSoC2021
This project aims at building a chatbot that can query the DBpedia based on the (DBQNA) dataset, Using Natural language as well as Query language so...
Contributor
Zhipeng Zhao
Mentor
Luca Virgili
Organization
DBpedia
Social Knowledge Graph: Employing SNA measures to Knowledge Graph
When novice users use DBpedia for querying, the information they really want is always overwhelmed by numerous query results. In this project, we...
Contributor
José Manuel Díaz Urraco
Mentor
Said Polanco-Martagón, Maribel, Beyza Yaman, Julio Hernandez, Jan Forberg
Organization
DBpedia
DBpedia Spotlight Dashboard: an integrated statistical information tool from the Wikipedia dumps and the DBpedia Extraction Framework artifacts
DBpedia Spotlight was released in 2011 by DBpedia. It is a tool that allows to annotate DBpedia resources in text, providing a solution for linking...
Contributor
Jayesh Desai
Mentor
Ram G Athreya, Andreas Both, Aleksandr Perevalov, Ricardo Usbeck
Organization
DBpedia
Modular DBpedia Chatbot
The project aims at extend the functionality of the current DBpedia chatbot by integrating the ecosystem of the Qanary framework including its...
Contributor
Karan Kharecha
Mentor
Krishanu Konar, Jan Forberg, Luca Virgili
Organization
DBpedia
User Centric Knowledge Engineering and Data Visualization
The ontologies dashboard was developed last year to show the statistics of the data in an interactive manner for helping community members to get a...
Contributor
Sahan Dilshan
Mentor
Edgard Marx, Lahiru Hinguruduwa
Organization
DBpedia
Lifecycle Management of DBpedia Neural QA Models - Sahan Dilshan
DBNQA is a large database that can be used to create question answering models. Using a question answering model like NSPM, we can create and...
Contributor
Ziwei XU
Mentor
Tommaso Soru, Thiago Castro Ferreira, Zheyuan BAI
Organization
DBpedia
Towards a neural extraction framework
In the large majority of cases in DBpedia, it is not clear what kind of relationship exists between the entities. Instead of extracting the triples ...