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

    <