Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader

by   Wenhan Xiong, et al.
The Regents of the University of California

We propose a new end-to-end question answering model, which learns to aggregate answer evidence from an incomplete knowledge base (KB) and a set of retrieved text snippets. Under the assumptions that the structured KB is easier to query and the acquired knowledge can help the understanding of unstructured text, our model first accumulates knowledge of entities from a question-related KB subgraph; then reformulates the question in the latent space and reads the texts with the accumulated entity knowledge at hand. The evidence from KB and texts are finally aggregated to predict answers. On the widely-used KBQA benchmark WebQSP, our model achieves consistent improvements across settings with different extents of KB incompleteness.


page 1

page 2

page 3

page 4


Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks

Existing question answering methods infer answers either from a knowledg...

Knowledge Base Completion using Web-Based Question Answering and Multimodal Fusion

Over the past few years, large knowledge bases have been constructed to ...

A Question Answering System Using Graph-Pattern Association Rules (QAGPAR) On YAGO Knowledge Base

A question answering system (QA System) was developed that uses graph-pa...

A Method of Query Graph Reranking for Knowledge Base Question Answering

This paper presents a novel reranking method to better choose the optima...

Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering

Question Answering (QA) models over Knowledge Bases (KBs) are capable of...

CBR-iKB: A Case-Based Reasoning Approach for Question Answering over Incomplete Knowledge Bases

Knowledge bases (KBs) are often incomplete and constantly changing in pr...

Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidence

Question answering models can use rich knowledge sources – up to one hun...

Code Repositories


PyTorch implementation of the ACL 2019 paper "Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader"

view repo

Please sign up or login with your details

Forgot password? Click here to reset