DEANNA: DEep Answers for maNy Naturally Asked questions

DEANNA is a framework for natural language question answering over structured knowledge bases. Given a natural language question, DEANNA translates questions into a SPARQL-like structured query language that can be evaluated over the Yago knowledge base.

Please view the screencast in 720p full screen. The video has been edited to make the screencast shorter.

• Mohamed Yahya, Klaus Berberich, Shady Elbassuoni, Maya Ramanath, Volker Tresp, Gerhard Weikum
  "Natural Language Questions for the Web of Data"
  (PDF, presentation: PPTX • animated PDF • unanimated PDF)
  2012 Conference on Empirical Methods in Natural Language Processing and Natural Language Learning (EMNLP 2012)
• Mohamed Yahya, Klaus Berberich, Shady Elbassuoni, Maya Ramanath, Volker Tresp, Gerhard Weikum
  "Deep Answers for Naturally Asked Questions on the Web of Data"
  (PDF, poster)
  Demo paper, 21st International World Wide Web Conference (WWW 2012)