高级检索
    孙亚伟, 程龚, 厉肖, 瞿裕忠. 基于图匹配网络的可解释知识图谱复杂问答方法[J]. 计算机研究与发展, 2021, 58(12): 2673-2683. DOI: 10.7544/issn1000-1239.2021.20211004
    引用本文: 孙亚伟, 程龚, 厉肖, 瞿裕忠. 基于图匹配网络的可解释知识图谱复杂问答方法[J]. 计算机研究与发展, 2021, 58(12): 2673-2683. DOI: 10.7544/issn1000-1239.2021.20211004
    Sun Yawei, Cheng Gong, Li Xiao, Qu Yuzhong. Graph Matching Network for Interpretable Complex Question Answering over Knowledge Graphs[J]. Journal of Computer Research and Development, 2021, 58(12): 2673-2683. DOI: 10.7544/issn1000-1239.2021.20211004
    Citation: Sun Yawei, Cheng Gong, Li Xiao, Qu Yuzhong. Graph Matching Network for Interpretable Complex Question Answering over Knowledge Graphs[J]. Journal of Computer Research and Development, 2021, 58(12): 2673-2683. DOI: 10.7544/issn1000-1239.2021.20211004

    基于图匹配网络的可解释知识图谱复杂问答方法

    Graph Matching Network for Interpretable Complex Question Answering over Knowledge Graphs

    • 摘要: 知识图谱问答是人工智能领域的研究热点之一.在该任务中,自然语言问句结构与知识图谱结构之间的语义匹配是一个具有挑战的研究问题.现有工作主要利用深度学习技术对自然语言问句进行序列化编码,然后与知识图谱子图计算语义匹配,这样做法未充分利用复杂问句的结构信息,方法也缺乏可解释性.针对此问题,提出一种基于图匹配网络的知识图谱复杂问答方法TTQA.首先,通过语法分析方法,构建一个与知识图谱无关的未定查询图.然后,依据未定查询图和给定的知识图谱,构建一个与知识图谱相关的已定查询图,在其中,提出一种图匹配网络GMN,通过结合预训练语言模型和图神经网络技术,再利用注意力机制学习查询结构的上下文表示,从而得到更加丰富的结构匹配表示,用于已定查询图预测.在2个复杂问答数据集LC-QuAD 1.0和ComplexWebQuestions 1.1进行实验,结果表明:TTQA超过了现有方法.同时,通过消融实验验证了GMN的有效性.此外,TTQA生成的未定结构图和已定查询图增强了问答系统可解释性.

       

      Abstract: Question answering over knowledge graphs is a trending research topic in artificial intelligence. In this task, the semantic matching between the structures of a natural language question and a knowledge graph is a challenging research problem. Existing works mainly use a sequence-based deep neural encoder to process questions. They construct a semantic matching model to compute the similarity between question structures and subgraphs of a knowledge graph. However, they could not exploit the structure of a complex question, and they lack interpretability. To alleviate this issue, this paper presents a graph matching network (GMN) based method for answering complex questions of a knowledge graph, called TTQA. This method firstly constructs an ungrounded query graph which is independent of the knowledge graph via syntactic parsing. Then, based on the ungrounded query graph and the knowledge graph, this method constructs a grounded query graph which is dependent on the knowledge graph. In particular, this paper proposes a cross-graph attention GMN which combines pre-trained language model and graph neural network to learn the context representation of a query. The context representation enhances the representation of graph matching which helps to predict a grounded query. Experimental results show that TTQA achieves state-of-the-art results on LC-QuAD 1.0 and ComplexWebQuestions 1.1. Ablation studies demonstrate the effectiveness of GMN. In addition, TTQA keeps the ungrounded query and the grounded query to enhance the interpretability of question answering.

       

    /

    返回文章
    返回