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

07/01/2022
by   Wenhu Chen, et al.
0

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.

READ FULL TEXT
research
09/28/2021

SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases

Knowledge Base Question Answering (KBQA) tasks that in-volve complex rea...
research
12/03/2020

Question Answering over Knowledge Bases by Leveraging Semantic Parsing and Neuro-Symbolic Reasoning

Knowledge base question answering (KBQA) is an important task in Natural...
research
05/21/2020

RuBQ: A Russian Dataset for Question Answering over Wikidata

The paper presents RuBQ, the first Russian knowledge base question answe...
research
10/25/2021

Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning

Knowledge Base Question Answering (KBQA) aims to answer userquestions fr...
research
02/25/2020

Differentiable Reasoning over a Virtual Knowledge Base

We consider the task of answering complex multi-hop questions using a co...
research
10/30/2017

Indirect Supervision for Relation Extraction using Question-Answer Pairs

Automatic relation extraction (RE) for types of interest is of great imp...
research
04/02/2021

Type Prediction Systems

Inferring semantic types for entity mentions within text documents is an...

Please sign up or login with your details

Forgot password? Click here to reset