Photo credit: Anna Logue
Seminar on Knowledge Graph Construction (FSS 2023)
Knowledge graphs – both general public knowledge graphs as well as system and domain specific ones – have been identified as useful ingredients for artificial intelligence systems. Especially the latest reported experiments with ChatGPT have shown that AIs need a solid backbone of trusted factual knowledge. In this seminar, we will look at the more practical aspects of how to build such knowledge graphs.
It is expected that participants in this seminar are familiar with the basic concepts of knowledge graphs and the underlying theories and standards, either by having attended the lecture IE 650 Knowledge Graphs or by an equivalent amount of self study.
Goals
In this seminar, you will familiarize yourself with approaches to knowledge graph construction. You will read research papers, specifications, and tool descriptions, as well as conduct own experiments where applicable, and you will discuss the insights with the other participants of the seminar.
As a participant, you are supposed to introduce a particular technique for knowledge graph construction and present it to the seminar participants. Each seminar paper undergoes a peer review process in the seminar. Presentations are supposed to be about 25 minutes long.
Organization
This seminar is organized by Prof. Dr. Heiko Paulheim
Available for Master students (2 SWS, 4 ECTS)
Prerequisites: IE 650 Knowledge Graphs
Additional resources:
Schedule
- February 23rd, 13:45–15:15: kick off meeting, room tba
- March 1st: topic assignment
- March 29th: paper draft due
- April 12th: peer review due
- May 4th, 11th, 18th, 25th: 13:45–17:00 presentations and discussions, schedule and room tba
- June 18th: final paper due
Registration
- Registration will be available in Portal2
- Note that this seminar is an in person event, so that you should only select it if you are planning to be in Mannheim in the spring term
- After the kick off session, please send a ranked list of three topics you would like to read and present in the seminar to Bianca Lermer
- Final assignment of topics will be made after the kick off meeting
Topics
Note: the topic list below does contains one or more literature pointers per topic as an entry point. These pointers are examples; you are expected to explore the literature about the topic, including predecessors, follow up works, documented use cases, etc.
Topic Literature Pointers Knowledge graph creation from databases Paper on D2RQ, Paper on Ontop Introduction to RML and R2RML Paper on RML, Comparison of RML and R2RML, RML Specification Knowledge graph construction tools based on RML Paper on RocketRML, Paper on SDM-RDFizer Knowledge graph creation from spreadsheets openrefine Website, RDF extension for openrefine Knowledge graph creation from Wikipedia and other Wikis Paper on DBpedia, Paper on YAGO, Paper on DBkWik Knowledge graph creation from other structured data any23 Website, paper on SPARQL anything, paper on KGTK Knowledge graph creation from text: classic approaches Paper on TextRunner, paper on ReVerb, paper on OLLIE Knowledge graph creation from text: more classic approaches Paper on ClausIE, paper on MinIE Knowledge graph creation from text: advanced approaches before BERT Survey paper Knowledge graph creation from text: advanced approaches since BERT Survey paper Knowledge extraction from the Deep Web Paper on DeepDive Knowledge graph validation Paper on ShEx, SHACL Specification All sources are available from the university network/
VPN.