← Go back

KBQA

Project Group Master

The Goal of this Project Group is to develop a Question Answering system based on Knowledge Graphs (KBs) like DBpedia(https://www.dbpedia.org/). An example for a KBQA system is TeBaQA

In general this contains:

  • Extracting entities from a natural language question
  • Link those entities and relations to a KB
  • Generating a SPARQL-Query

Furthermore the answers from the system should be evaluated. For that the GERBIL-QA system (http://gerbil-qa.aksw.org/gerbil/ ) should be used.

Question & Answer Session

Q: Will there be prior assignments? What would these assignments look like?
A: Yes, there will be assignments to ensure that participants are able to implement the required components. To this end, the assignments will contain some general questions and a programming task in Python.

Q: Is there a seminar connected to this PG?
A: No.

Q: What are the prerequisites for this PG?
A: You should be able to program in Java or Python. Knowledge about RDF, Knowledge Graphs, Natural Language processing and Machine Learning are beneficial. If you don't know these things you will have to study it at the beginning of the PG. Unfortunately, there won't be the time to give an introduction into these topics.

In case you have further questions, feel free to contact Daniel Vollmers or Nikit Srivastava

Course in PAUL

L.079.07055 Projektgruppe: Knowledge base question answering (in English)