KBQA论文综述及实现方法（~ing）

核心方法

Traditional Methods

• Semantic parsing on freebase from question- answer pairs(2013)
• More accurate question answering on free- base(2015)
• Automated template generation for question answering over knowledge graphs(2017)

Information Retrieval-based (IR)

• Feature Engineering

  • Informationextractionoverstructureddata:Questionanswer- ing with freebase(2014)

• Representation Learning

  • one-hop reasoning

    • Question Answering with Subgraph Embed- dings(2014)
    • Question answering over freebase with multi- column convolutional neural networks(2015)
    • An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge(2017)

  • Incorporating External Knowledge

    • Complex Embeddings for Simple Link Pre- diction(2016)
    • Question Answering on Freebase via Relation Extraction and Textual Evidence(2016
    • Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text(2018)
    • PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text(2019)
    • Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings(2020)

  • Mutli-hop reasoning

    • Weakly supervised memory networks
    • Large-scale simple question answering with memory networks(2015)
    • Memory networks(2015)
    • Key-Value Memory Networks for Directly Reading Documents(2016)
    • Bidirectional Attentive Memory Networks for Ques- tion Answering over Knowledge Bases(2015)
    • Stepwise Reasoning for Multi-Relation Question Answering over Knowledge Graph with Weak Supervision(2020)

Neural Semantic Parsing-based (NSP)

• Query Graph

  • Large-scale semantic parsing without question-answer pairs(2014)
  • Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base(2015)
  • Constraint-based question answering with knowledge graph(2016)
  • Improved Neural Relation Detection for Knowledge Base Question Answering(2017)
  • Knowledge base question answering via encoding of complex query graphs(2018)
  • Learning to rank query graphs for complex question answering over knowledge graphs.(2019)
  • Knowledge-based question answering by tree-to-sequence learning(2020)
  • A state-transition framework to answer complex questions over knowledge base(2018)
  • Learning to answer complex questions over knowledge bases with query composition(2019)
  • Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases(2020)
  • The Web as a Knowledge-Base for Answering Complex Questions(2018)

• Encoder-Decoder Method

  • Language to Logical Form with Neural Attention(2016)
  • Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model(2018)
  • Neural symbolic machines: Learning semantic parsers on freebase with weak supervision(2017)

Other

• The Web as a Knowledge-Base for Answering Complex Questions(2018)
• Enhancing Key-Value Memory Neural Networks for Knowledge Based Question Answering(2019)

Dataset

WebQuestion

• Semantic parsing on freebase from question- answer pairs(2013)

ComplexQuestions

• Constraint-based question answering with knowledge graph(2016)

WebQuestionsSP

• The value of semantic parse labeling for knowledge base question answering(2016)

ComplexWebQuestions

• The Web as a Knowledge-Base for Answering Complex Questions(2018)

QALD

LC-QuAD

• Lc-quad: A corpus for complex question answering over knowledge graphs(2017)

LC-QuAD 2.0

• Lc-quad 2.0: A large dataset for complex question answering over wikidata and DBpedia(2019)

参考文献

• A Survey on Complex Question Answering over Knowledge Base-Recent Advances and Challenges.pdf