Complex Knowledge Base Question Answering: A Survey

2021/08/15 by Yunshi Lan, Lan, Yunshi, Gaole He +9 · 12 citations
Computer Science · #Advanced Graph Neural Networks #Natural Language Processing Techniques #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.2108.06688

20 pages, 4 tables, 7 figures. arXiv admin note: text overlap with arXiv:2105.11644

arxiv created 2022/11/08 · arxiv updated 2022/11/09

Abstract

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 performance on complex questions is 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 on 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 describe benchmark datasets for complex KBQA task and introduce the construction process of these datasets. Next, 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 major differences and similarities. After that, we summarize the challenges that these two categories of methods encounter when answering complex questions, and explicate advanced solutions and techniques used in existing work. Finally, we conclude and discuss several promising directions related to complex KBQA for future research.

Citations

• On Information and Sufficiency
• Sequence to Sequence Learning with Neural Networks
• Variational Reasoning for Question Answering with Knowledge Graph
• A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges
• A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions

Cited by

• SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs
• KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
• Plan of Knowledge: Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering
• ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG
• How Accurate Are LLMs at Multi-Question Answering on Conversational Transcripts?
• GGC: Selective Query Correction for Reliable Text-to-SPARQL Generation
• Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems
• Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE
• Towards Unified Neurosymbolic Reasoning on Knowledge Graphs
• An Iterative Question-Guided Framework for Knowledge Base Question Answering
• Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering
• Enhancing Large Language Models with Reward-guided Tree Search for Knowledge Graph Question and Answering

Related

• A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions
• A Survey on Complex Question Answering over Knowledge Base: Recent Advances and Challenges
• Knowledge Base Question Answering: A Semantic Parsing Perspective
• Beyond Chains: Bridging Large Language Models and Knowledge Bases in Complex Question Answering
• A Two-Stage Approach towards Generalization in Knowledge Base Question Answering