Complex knowledge base question answering: A survey

Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Early studies mainly focused on answering simple questions over KBs and achieved great success. However, their performances on complex questions are still far from satisfactory. Therefore, in recent years,...

Full description

Saved in:
Bibliographic Details
Main Authors: LAN, Yunshi, HE, Gaole, JIANG, Jinhao, JIANG, Jing, XIN, Zhao Wayne, WEN, Ji Rong
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
TV
Online Access:https://ink.library.smu.edu.sg/sis_research/7762
https://ink.library.smu.edu.sg/context/sis_research/article/8765/viewcontent/ComplexKnowledgeBase_2022_av.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-8765
record_format dspace
spelling sg-smu-ink.sis_research-87652024-02-28T08:06:44Z Complex knowledge base question answering: A survey LAN, Yunshi HE, Gaole JIANG, Jinhao JIANG, Jing XIN, Zhao Wayne WEN, Ji Rong Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Early studies mainly focused on answering simple questions over KBs and achieved great success. However, their performances on complex questions are still far from satisfactory. Therefore, in recent years, researchers propose a large number of novel methods, which looked into the challenges of answering complex questions. In this survey, we review recent advances in KBQA with the focus on solving complex questions, which usually contain multiple subjects, express compound relations, or involve numerical operations. In detail, we begin with introducing the complex KBQA task and relevant background. Then, we present two mainstream categories of methods for complex KBQA, namely semantic parsing-based (SP-based) methods and information retrieval-based (IR-based) methods. Specifically, we illustrate their procedures with flow designs and discuss their difference and similarity. Next, we summarize the challenges that these two categories of methods encounter when answering complex questions, and explicate advanced solutions as well as techniques used in existing work. After that, we discuss the potential impact of pre-trained language models (PLMs) on complex KBQA. To help readers catch up with SOTA methods, we also provide a comprehensive evaluation and resource about complex KBQA task. Finally, we conclude and discuss several promising directions related to complex KBQA for future research 2023-11-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/7762 info:doi/10.1109/TKDE.2022.3223858 https://ink.library.smu.edu.sg/context/sis_research/article/8765/viewcontent/ComplexKnowledgeBase_2022_av.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Cognition Compounds Knowledge base knowledge base question answering Knowledge based systems natural language processing question answering Question answering (information retrieval) Semantics survey Task analysis TV Databases and Information Systems Numerical Analysis and Scientific Computing
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Cognition
Compounds
Knowledge base
knowledge base question answering
Knowledge based systems
natural language processing
question answering
Question answering (information retrieval)
Semantics
survey
Task analysis
TV
Databases and Information Systems
Numerical Analysis and Scientific Computing
spellingShingle Cognition
Compounds
Knowledge base
knowledge base question answering
Knowledge based systems
natural language processing
question answering
Question answering (information retrieval)
Semantics
survey
Task analysis
TV
Databases and Information Systems
Numerical Analysis and Scientific Computing
LAN, Yunshi
HE, Gaole
JIANG, Jinhao
JIANG, Jing
XIN, Zhao Wayne
WEN, Ji Rong
Complex knowledge base question answering: A survey
description Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB). Early studies mainly focused on answering simple questions over KBs and achieved great success. However, their performances on complex questions are still far from satisfactory. Therefore, in recent years, researchers propose a large number of novel methods, which looked into the challenges of answering complex questions. In this survey, we review recent advances in KBQA with the focus on solving complex questions, which usually contain multiple subjects, express compound relations, or involve numerical operations. In detail, we begin with introducing the complex KBQA task and relevant background. Then, we present two mainstream categories of methods for complex KBQA, namely semantic parsing-based (SP-based) methods and information retrieval-based (IR-based) methods. Specifically, we illustrate their procedures with flow designs and discuss their difference and similarity. Next, we summarize the challenges that these two categories of methods encounter when answering complex questions, and explicate advanced solutions as well as techniques used in existing work. After that, we discuss the potential impact of pre-trained language models (PLMs) on complex KBQA. To help readers catch up with SOTA methods, we also provide a comprehensive evaluation and resource about complex KBQA task. Finally, we conclude and discuss several promising directions related to complex KBQA for future research
format text
author LAN, Yunshi
HE, Gaole
JIANG, Jinhao
JIANG, Jing
XIN, Zhao Wayne
WEN, Ji Rong
author_facet LAN, Yunshi
HE, Gaole
JIANG, Jinhao
JIANG, Jing
XIN, Zhao Wayne
WEN, Ji Rong
author_sort LAN, Yunshi
title Complex knowledge base question answering: A survey
title_short Complex knowledge base question answering: A survey
title_full Complex knowledge base question answering: A survey
title_fullStr Complex knowledge base question answering: A survey
title_full_unstemmed Complex knowledge base question answering: A survey
title_sort complex knowledge base question answering: a survey
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/7762
https://ink.library.smu.edu.sg/context/sis_research/article/8765/viewcontent/ComplexKnowledgeBase_2022_av.pdf
_version_ 1794549718047522816