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

Wenhu Chen, William W. Cohen, Michiel De Jong, Nitish Gupta, Alessandro Presta +2 more
7/1/2022
cs.AI

No confident code implementation found for this paper. 4 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 4 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text

82% match2023

KARLA: Knowledge-base Augmented Retrieval for Language Models

80% match2026

Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases

80% match1 repo1722019

Ask To The Point: Open-Domain Entity-Centric Question Generation

79% match1 repo42023

Two is Better Than One: Answering Complex Questions by Multiple Knowledge Sources with Generalized Links

79% match2023

A Practical Entity Linking System for Tables in Scientific Literature

79% match2023

Cite this paper

@article{chen2022questionanswer,
  title  = {QA Is the New KR: Question-Answer Pairs as Knowledge Bases},
  author = {Wenhu Chen and William W. Cohen and Michiel De Jong and Nitish Gupta and Alessandro Presta and Pat Verga and John Wieting},
  year   = {2022},
  eprint = {2207.00630},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2207.00630v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2207.00630.svg)](https://codeofpaper.com/paper/2207.00630)

Discussion