QA Is the New KR: Question-Answer Pairs as Knowledge Bases
William W. Cohen, Wenhu Chen, Michiel De Jong, Nitish Gupta, Alessandro Presta, Pat Verga, John Wieting
Abstract
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.
BibTeX
@article{Cohen_Chen_De Jong_Gupta_Presta_Verga_Wieting_2024, title={QA Is the New KR: Question-Answer Pairs as Knowledge Bases}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26794}, DOI={10.1609/aaai.v37i13.26794}, abstractNote={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.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Cohen, William W. and Chen, Wenhu and De Jong, Michiel and Gupta, Nitish and Presta, Alessandro and Verga, Pat and Wieting, John}, year={2024}, month={Jul.}, pages={15385-15392} }