基于层次结构图的多跳知识图谱问答模型

doi:10.19678/j.issn.1000-3428.0066637

摘要/Abstract

摘要：

知识图谱问答（KBQA）旨在理解用户的自然语言问句，在结构化的知识图谱中通过检索、推理等手段来获取答案实体。近年来，多跳KBQA备受关注，然而，复杂问句中通常存在多个关系意图，已有KBQA方法大多忽视了推理关系链的关系顺序问题。为此，提出一种基于层次结构图的多跳知识图谱问答模型（HSG-KBQA），建模自然语言问句的关系层次顺序，指导模型在每个推理步选择合理的关系意图。设计一种层次结构图，显式地体现问句中关系的层次距离，利用LSTM-BiGCN编码层将词语间的依存信息编码到问句中；提出虚拟节点的概念，利用图池化技术过滤不重要的节点，学习推理过程中知识图谱的状态；设计基于注意力机制和层次权重的解码器来优化指令生成，使推理指令更匹配问句中的关系链顺序。实验结果表明，HSG-KBQA在WebQuestionsSP数据集上取得了71.3%的Hits@1分数，在PathQuestions数据集上取得了97.3%（PQ-2H）和89.7%（PQ-3H）的Hits@1分数，均优于对照基准模型，表明HSG-KBQA模型在KBQA任务中具有更好的性能。

关键词: 知识图谱问答, 问答系统, 多跳问答, 图神经网络, 动态推理

Abstract:

Knowledge Base Question Answering(KBQA) aims to interpret natural language questions and obtain answer entities via retrieval and inference in a Knowledge Graph (KG). Recently, considerable attention has been given to multi-hop KBQA, which faces a significant, yet often overlooked challenge: complex questions typically contain multiple relational intentions with an inferential order that is frequently ignored. To address this challenge, this paper proposes a multi-hop KBQA model based on a Hierarchical Structure Graph(HSG-KBQA). This model is designed to recognize and guide the relational hierarchical order of natural language questions, enabling the selection of appropriate relational intents at each inference step. The proposed hierarchical structure graph explicitly represents the relational hierarchical order in questions and encodes the dependency information into the question using an LSTM-BiGCN encoding layer. Furthermore, the concept of a virtual node is introduced to learn the state of the KG during inference utilizing graph pooling techniques. Additionally, an attention mechanism-based decoder with hierarchical weights is presented, aiming to optimize instruction generation. This ensures that each hop instruction aligns more accurately with the relational chain order in the question. Experimental results show that the HSG-KBQA model demonstrates superior performance, achieving Hits@1 scores of 71.3% on the WebQuestionsSP dataset and 97.3%(PQ-2H) and 89.7%(PQ-3H) on the PathQuestions dataset. These results are superior to those of the benchmark model, indicating the enhanced capability of the proposed model in handling the KBQA task.

Key words: Knowledge Base Question Answering(KBQA), question answering system, multi-hop question answering, graph neural network, dynamic reasoning

刘昀抒, 申彦明, 齐恒, 尹宝才. 基于层次结构图的多跳知识图谱问答模型[J]. 计算机工程, 2024, 50(1): 101-109.

Yunshu LIU, Yanming SHEN, Heng QI, Baocai YIN. Multi-hop Knowledge Base Question Answering Model Based on Hierarchical Structure Graph[J]. Computer Engineering, 2024, 50(1): 101-109.

https://www.ecice06.com/CN/Y2024/V50/I1/101

图/表 8

图1 HSG-KBQA模型整体框架

Fig.1 Overall framework of HSG-KBQA model

图2 依存句法树和层次结构图

Fig.2 The dependency tree and hierarchical structure graph

图3 图池化模块结构

Fig.3 Structure of graph pooling module

图4 损失函数曲线

Fig.4 Loss function curves

参考文献 36

1	吴天波, 刘露平, 罗晓东, 等. 基于弱依赖信息的知识库问答方法. 计算机工程, 2021, 47(6): 76- 82. URL
	WU T B, LIU L P, LUO X D, et al. Knowledge base question answering method based on weak dependency information. Computer Engineering, 2021, 47(6): 76- 82. URL
2	吴天波, 周欣, 程军军, 等. 基于位置和注意力联合表示的知识图谱问答. 计算机工程, 2022, 48(8): 98-104, 112. URL
	WU T B, ZHOU X, CHENG J J, et al. Knowledge graph question-answering based on joint location and attention representation. Computer Engineering, 2022, 48(8): 98-104, 112. URL
3	BORDES A, USUNIER N, CHOPRA S, et al. Large-scale simple question answering with memory networks[EB/OL]. [2022-11-05]. https://arxiv.org/abs/1506.02075.pdf.
4	DONG L, WEI F R, ZHOU M, et al. Question answering over Freebase with multi-column convolutional neural networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. [S. l. ]: Association for Computational Linguistics, 2015: 260-269.
5	LAN Y S, WANG S H, JIANG J. Knowledge base question answering with topic units[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence. Washington D. C., USA: IEEE Press, 2019: 5046-5052.
6	MAHESHWARI G, TRIVEDI P, LUKOVNIKOV D, et al. Learning to rank query graphs for complex question answering over knowledge graphs[EB/OL]. [2022-11-05]. https://arxiv.org/abs/1811.01118.
7	QIU Y Q, ZHANG K, WANG Y Z, et al. Hierarchical query graph generation for complex question answering over knowledge graph[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management. New York, USA: ACM Press, 2020: 1285-1294.
8	LUO K Q, LIN F L, LUO X S, et al. Knowledge base question answering via encoding of complex query graphs[C]//Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing. [S. l. ]: Association for Computational Linguistics, 2018: 2185-2194.
9	JIN W, ZHAO B, YU H, et al. Improving embedded knowledge graph multi-hop question answering by introducing relational chain reasoning[EB/OL]. [2022-11-05]. https://arxiv.org/abs/2110.12679.pdf.
10	DREW A H, CHRISTOPHER D. Learning by abstraction: the neural state machine[C]//Proceedings of 2019 Conference on Neural Information Processing Systems. New York, USA: ACM Press, 2019: 5901-5914.
11	HAN J L, CHENG B, WANG X. Two-phase hypergraph based reasoning with dynamic relations for multi-hop KBQA[C]//Proceedings of the 29th International Joint Conference on Artificial Intelligence. New York, USA: ACM Press, 2020: 3615-3621.
12	HAN J L, CHENG B, WANG X. Open domain question answering based on text enhanced knowledge graph with hyperedge infusion[EB/OL]. [2022-11-05]. https://aclanthology.org/2020.findings-emnlp.133/.
13	YIH W T, CHANG M W, HE X D, et al. Semantic parsing via staged query graph generation: question answering with knowledge base[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. [S. l. ]: Association for Computational Linguistics, 2015: 1321-1331.
14	LAN Y S, JIANG J. Query graph generation for answering multi-hop complex questions from knowledge bases[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. [S. l. ]: Association for Computational Linguistics, 2020: 969-974.
15	SUN Y W, ZHANG L L, CHENG G, et al. SPARQA: skeleton-based semantic parsing for complex questions over knowledge bases. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(5): 8952- 8959. doi: 10.1609/aaai.v34i05.6426
16	KAPANIPATHI P, ABDELAZIZ I, RAVISHANKAR S. Question answering over knowledge bases by leveraging semantic parsing and neuro-symbolic reasoning[EB/OL]. [2022-11-05]. https://arxiv.org/abs/2012.01707.
17	张鹏举, 贾永辉, 陈文亮. 基于多特征实体消歧的中文知识图谱问答. 计算机工程, 2022, 48(2): 47- 54. URL
	ZHANG P J, JIA Y H, CHEN W L. Chinese knowledge based question answering based on multi-feature entity disambiguation. Computer Engineering, 2022, 48(2): 47- 54. URL
18	SUN H T, DHINGRA B, ZAHEER M, et al. Open domain question answering using early fusion of knowledge bases and text[C]//Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing. [S. l. ]: Association for Computational Linguistics, 2018: 4231-4242.
19	SAXENA A, TRIPATHI A, TALUKDAR P. Improving multi-hop question answering over knowledge graphs using knowledge base embeddings[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. [S. l. ]: Association for Computational Linguistics, 2020: 4498-4507.
20	TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[C]//Proceedings of the 33rd International Conference on Machine Learning. New York, USA: ACM Press, 2016: 2071-2080.
21	MILLER A, FISCH A, DODGE J, et al. Key-value memory networks for directly reading documents[C]//Proceedings of 2016 Conference on Empirical Methods in Natural Language Processing. [S. l. ]: Association for Computational Linguistics, 2016: 1400-1409.
22	ZHOU M T, HUANG M L, ZHU X Y. An interpretable reasoning network for multi-relation question answering[C]//Proceedings of the 27th International Conference on Computational Linguistics. [S. l. ]: Association for Computational Linguistics, 2018: 2010-2022.
23	QIU Y Q, WANG Y Z, JIN X L, et al. Stepwise reasoning for multi-relation question answering over knowledge graph with weak supervision[C]//Proceedings of the 13th International Conference on Web Search and Data Mining. New York, USA: ACM Press, 2020: 474-482.
24	HE G L, LAN Y S, JIANG J, et al. Improving multi-hop knowledge base question answering by learning intermediate supervision signals[C]//Proceedings of the 14th ACM International Conference on Web Search and Data Mining. New York, USA: ACM Press, 2021: 553-561.
25	孙水发, 李小龙, 李伟生, 等. 图神经网络应用于知识图谱推理的研究综述. 计算机科学与探索, 2023, 17(1): 27- 52.
	SUN S F, LI X L, LI W S, et al. Review of graph neural networks applied to knowledge graph reasoning. Journal of Frontiers of Computer Science & Technology, 2023, 17(1): 27- 52.
26	HOCHREITER S, SCHMIDHUBER J. Long short-term memory. Neural Computation, 1997, 9(8): 1735- 1780.
27	FU T J, LI P H, MA W Y. GraphRel: modeling text as relational graphs for joint entity and relation extraction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. [S. l. ]: Association for Computational Linguistics, 2019: 1409-1418.
28	LEE J, LEE I, KANG J. Self-attention graph pooling[C]//Proceedings of the 36th International Conference on Machine Learning. New York, USA: ACM Press, 2019: 3734-3743.
29	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the 5th International Conference on Learning Representations. New York, USA: ACM Press, 2017: 126-135.
30	SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[EB/OL]. [2022-11-05]. https://arxiv.org/abs/1703.06103.
31	KULLBACK S, LEIBLER R A. On information and sufficiency. The Annals of Mathematical Statistics, 1951, 22(1): 79- 86.
32	YIH W T, RICHARDSON M, MEEK C, et al. The value of semantic parse labeling for knowledge base question answering[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. [S. l. ]: Association for Computational Linguistics, 2016: 201-206.
33	CAI J Y, ZHANG Z Q, WU F. Deep cognitive reasoning network for multi-hop question answering over knowledge graph[C]//Proceedings of the 59th Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing. [S. l. ]: Association for Computational Linguistics, 2021: 219-229.
34	CN J E, MEI S J, HU X R, et al. Seeing the wood for the trees: a contrastive regularization method for the low-resource knowledge base question answering[EB/OL]. [2022-11-05]. https://aclanthology.org/2022.findings-naacl.82.pdf.
35	DAS R, DHULIAWALA S, ZAHEER M, et al. Go for a walk and arrive at the answer: reasoning over paths in knowledge bases using reinforcement learning[EB/OL]. [2022-11-05]. https://arxiv.org/abs/1711.05851.pdf.
36	GUPTA A, ANNERVAZ K M, DUKKIPATI A, et al. An inference approach to question answering over knowledge graphs[EB/OL]. [2022-11-05]. https://arxiv.org/abs/2112.11070.pdf.

[1]	何杏宇, 周易歆, 罗东旭, 杨桂松. 基于图神经网络和多主体评价的教学资源推荐[J]. 计算机工程, 2024, 50(7): 13-22.
[2]	张正康, 杨丹, 聂铁铮, 寇月. 基于图结构聚类的自监督学习疾病诊断方法[J]. 计算机工程, 2024, 50(7): 360-371.
[3]	孙文洁, 李宗民, 孙浩淼. 基于图神经网络的多智能体强化学习值函数分解方法[J]. 计算机工程, 2024, 50(5): 62-70.
[4]	游奔, 李晓红, 姚锦, 冯绍杰. 基于多粒度图与注意力机制的半监督短文本分类[J]. 计算机工程, 2024, 50(5): 83-90.
[5]	张宝鑫, 杨丹, 聂铁铮, 寇月. 基于自监督的多视角图协同过滤推荐方法[J]. 计算机工程, 2024, 50(5): 100-110.
[6]	吴正洋, 张广涛, 黄立, 汤庸. 基于异质图嵌入和会话交互的课程推荐模型[J]. 计算机工程, 2024, 50(4): 95-103.
[7]	王华珍, 许泽, 孙悦, 丘斌, 陈坚, 邱强斌. 基于事件演化图的多标记事件预测模型[J]. 计算机工程, 2024, 50(4): 132-140.
[8]	王俊, 赖会霞, 万玥, 张仕. 基于角度的图神经网络高维数据异常检测方法[J]. 计算机工程, 2024, 50(3): 156-165.
[9]	王柏涵, 姜晓燕, 范柳伊. 基于深度监督隐空间构建的语义分割改进方法[J]. 计算机工程, 2024, 50(3): 191-199.
[10]	李伟健, 胡慧君. 基于潜在特征增强网络的视频描述生成方法[J]. 计算机工程, 2024, 50(2): 266-272.
[11]	吴志强, 解庆, 李琳, 刘永坚. 基于多模态融合的图神经网络推荐算法[J]. 计算机工程, 2024, 50(1): 91-100.
[12]	顾嘉静, 杨丹, 聂铁铮, 寇月. 基于多视图融合跨层对比学习的推荐算法[J]. 计算机工程, 2024, 50(1): 120-128.
[13]	刘晓黎, 王轶彤. 基于自监督学习的多密度图会话推荐[J]. 计算机工程, 2023, 49(9): 60-68, 78.
[14]	隋国华, 李陶然, 刘昊, 陈林, 汪卫. 基于图表示学习的领域知识图谱推理技术研究[J]. 计算机工程, 2023, 49(9): 89-98.
[15]	赵世豪, 毛国君, 熊保平, 黄山, 林江宏. 基于图小波卷积神经网络的时空图挖掘模型[J]. 计算机工程, 2023, 49(7): 85-93.

选择文件类型/文献管理软件名称

选择包含的内容