MuHeQA: Zero-shot Question Answering over Multiple and Heterogeneous Knowledge Bases

Tracking #: 3379-4593

Authors: 
Carlos Badenes-Olmedo
Oscar Corcho

Responsible editor: 
Guest Editors Interactive SW 2022

Submission type: 
Full Paper
Abstract: 
There are two main limitations in most of the existing Knowledge Graph Question Answering (KGQA) algorithms. First, the approaches depend heavily on the structure and cannot be easily adapted to other KGs. Second, the availability and amount of additional domain-specific data in structured or unstructured formats has also proven to be critical in many of these systems. Such dependencies limit the applicability of KGQA systems and make their adoption difficult. A novel algorithm is proposed, MuHeQA, that alleviates both limitations by retrieving the answer from textual content automatically generated from KGs instead of queries over them. This new approach (1) works on one or several KGs simultaneously, (2) does not require training data what makes it is domain-independent, (3) enables the combination of knowledge graphs with unstructured information sources to build the answer, and (4) reduces the dependency on the underlying schema since it does not navigate through structured content but only reads property values. MuHeQA extracts answers from textual summaries created by combining information related to the question from multiple knowledge bases, be them structured or not. Experiments over Wikidata and DBpedia show that our approach achieves comparable performance to other approaches in single-fact questions while being domain and KG independent. Results raise important questions for future work about how the textual content that can be created from knowledge graphs enables answer extraction.
Full PDF Version: 
Tags: 
Reviewed

Decision/Status: 
Accept

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Floriano Scioscia submitted on 02/Mar/2023
Suggestion:
Accept
Review Comment:

The revision has solved all my concerns with the manuscript. I believe it can be accepted for publication.

Review #2
By Takahira Yamaguchi submitted on 06/Mar/2023
Suggestion:
Minor Revision
Review Comment:

I am not sure how my first question has been solved in revised paper: Seeing this architecture, it is my first question why do you not take domain ontologies with knowledge graph. Because they present concept hierarchy and property semantics to KG, we would have QA systems with ontologies and KG.

Review #3
Anonymous submitted on 16/Mar/2023
Suggestion:
Accept
Review Comment:

I believe the authors addressed all the reviewers' comments, and the paper's quality has significantly improved.