QA Is the New KR: Question-Answer Pairs as Knowledge Bases


  • William W. Cohen Google AI
  • Wenhu Chen Google AI
  • Michiel De Jong Google AI
  • Nitish Gupta Google AI
  • Alessandro Presta Google AI
  • Pat Verga Google AI
  • John Wieting Google AI



Knowledge Representation, Question Answering, Reasoning, Natural Language Processing


We propose a new knowledge representation (KR) based on knowledge bases (KBs) derived from text, based on question generation and entity linking. We argue that the proposed type of KB has many of the key advantages of a traditional symbolic KB: in particular, it consists of small modular components, which can be combined compositionally to answer complex queries, including relational queries and queries involving ``multi-hop'' inferences. However, unlike a traditional KB, this information store is well-aligned with common user information needs. We present one such KB, called a QEDB, and give qualitative evidence that the atomic components are high-quality and meaningful, and that atomic components can be combined in ways similar to the triples in a symbolic KB. We also show experimentally that questions reflective of typical user questions are more easily answered with a QEDB than a symbolic KB.




How to Cite

Cohen, W. W., Chen, W., De Jong, M., Gupta, N., Presta, A., Verga, P., & Wieting, J. (2023). QA Is the New KR: Question-Answer Pairs as Knowledge Bases. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 15385-15392.