QA Is the New KR: Question-Answer Pairs as Knowledge Bases
This is an incremental approach that aims to improve knowledge representation for users by making it more accessible and aligned with common queries.
The paper proposes generating knowledge bases from text using question-answer pairs to address the misalignment between traditional symbolic KBs and user information needs, resulting in a modular and compositional structure capable of handling complex queries like relational and multi-hop inferences.
In this position paper, we propose a new approach to generating a type of knowledge base (KB) 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.