融合多跳关系路径信息的关系推理方法

doi:10.11772/j.issn.1001-9081.2020121905

计算机应用 ›› 2021, Vol. 41 ›› Issue (10): 2799-2805.DOI: 10.11772/j.issn.1001-9081.2020121905

所属专题：人工智能

融合多跳关系路径信息的关系推理方法

董永峰^1,2,3, 刘超^1,2,3, 王利琴^1,2,3, 李英双^1,2,3

1. 河北工业大学人工智能与数据科学学院, 天津 300401;
2. 河北省大数据计算重点实验室(河北工业大学), 天津 300401;
3. 河北省数据驱动工业智能工程研究中心(河北工业大学), 天津 300401

收稿日期:2020-12-08 修回日期:2021-05-06 出版日期:2021-10-10 发布日期:2021-07-14
通讯作者: 王利琴
作者简介:董永峰(1977-),男,河北定州人,教授,博士,CCF会员,主要研究方向:人工智能、知识图谱;刘超(1993-),男,山西晋中人,硕士研究生,主要研究方向:智能信息处理、知识图谱;王利琴(1980-),女,河北张北人,实验师,博士,CCF会员,主要研究方向:智能信息处理、知识图谱;李英双(1986-),女,河北衡水人,工程师,硕士,主要研究方向:智能信息处理。
基金资助:
国家自然科学基金资助项目（61806072）；天津市自然科学基金资助项目（19JCZDJC40000）；河北省高等学校科学技术研究项目（QN2021213）。

Relationship reasoning method combining multi-hop relationship path information

DONG Yongfeng^1,2,3, LIU Chao^1,2,3, WANG Liqin^1,2,3, LI Yingshuang^1,2,3

1. School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China;
2. Hebei Province Key Laboratory of Big Data Calculation(Hebei University of Technology), Tianjin 300401, China;
3. Hebei Data Driven Industrial Intelligent Engineering Research Center(Hebei University of Technology), Tianjin 300401, China

Received:2020-12-08 Revised:2021-05-06 Online:2021-10-10 Published:2021-07-14
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61806072), the Natural Science Foundation of Tianjin City (19JCZDJC40000), the Science and Technology Research Project of Hebei Province Colleges and Universities (QN2021213).

摘要/Abstract

摘要： 针对目前知识图谱（KG）中存在大量关系的缺失，以及在进行关系推理时没有充分考虑两实体间多跳路径中隐含信息的问题，提出了一种融合多跳关系路径信息的关系推理方法。首先，对于给定的候选关系和两个实体，利用卷积运算将连接两个实体的多跳关系路径编码到低维空间里并提取信息；其次，利用双向长短时记忆（BiLSTM）网络建模以生成关系路径表示向量，并利用注意力机制将其与候选关系表示向量进行组合；最后，采用多步推理方式找到匹配程度最高的关系作为推理结果并判断其精确率。与目前常用的路径排序算法（PRA）、神经网络模型Path-RNN以及强化学习模型MINERVA相比，在使用大型知识图谱数据集NELL995进行实验时，所提算法的平均精确率均值（MAP）分别提高了1.96、8.6和1.6个百分点；在使用小型知识图谱数据集Kinship进行实验时，所提方法的MAP比PRA、MINERVA分别提高了21.3、13和12.1个百分点。实验结果表明，所提算法能更加准确地推理出实体间的关系链接。

关键词: 知识图谱, 关系推理, 双向长短时记忆网络, 注意力机制, 卷积神经网络

Abstract: Concerning the problems of the lack of a large number of relationships in the current Knowledge Graph (KG), and the lack of full consideration of the hidden information in the multi-hop path between two entities when performing relationship reasoning, a relationship reasoning method combining multi-hop relationship path information was proposed. Firstly, for the given candidate relationships and two entities, the convolution operation was used to encode the multi-hop relationship path connecting the two entities into a low-dimensional space and extract the information. Secondly, the Bidirectional Long Short-Term Memory (BiLSTM) network was used for modeling to generate the relationship path representation vector, and the attention mechanism was used to combine it with the candidate relationship representation vector. Finally, a multi-step reasoning method was used to find the relationship with the highest matching degree as the reasoning result and judge its precision. Compared with the current popular Path Ranking Algorithm (PRA), the neural network model named Path-RNN and reinforcement learning model named MINERVA, the proposed algorithm had the Mean Average Precision (MAP) increased by 1.96,8.6 and 1.6 percentage points respectively when using the large-scale knowledge graph dataset NELL995 for experiments. And when using the small-scale knowledge graph dataset Kinship for experiments, the proposed algorithm had the MAP improved by 21.3,13 and 12.1 percentage points respectively compared to PRA and MINERVA. The experimental results show that the proposed method can infer the relationship links between entities more accurately.

Key words: Knowledge Graph (KG), relationship reasoning, Bidirectional Long Short-Term Memory (BiLSTM) network, attention mechanism, Convolutional Neural Network (CNN)

中图分类号:

TP391.1

董永峰, 刘超, 王利琴, 李英双. 融合多跳关系路径信息的关系推理方法[J]. 计算机应用, 2021, 41(10): 2799-2805.

DONG Yongfeng, LIU Chao, WANG Liqin, LI Yingshuang. Relationship reasoning method combining multi-hop relationship path information[J]. Journal of Computer Applications, 2021, 41(10): 2799-2805.

参考文献

[1] 刘峤, 李杨, 段宏, 等. 知识图谱构建技术综述[J]. 计算机研究与发展, 2016, 53(3):582-600.(LIU Q, LI Y, DUAN H, et al. Knowledge graph construction techniques[J]. Journal of Computer Research and Development, 2016, 53(3):582-600.)
[2] LAO N, MITCHELL T, COHEN W W. Random walk inference and learning in a large scale knowledge base[C]//Proceeding of the 2011 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2011:529-539.
[3] NEELAKANTAN A, ROTH B, McCALLUM A. Compositional vector space models for knowledge base completion[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics/the 7th International Joint Conference on Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2015:155-166.
[4] CHUA L O. CNN:a vision of complexity[J]. International Journal of Bifurcation and Chaos, 1997, 7(10):2219-2425.
[5] 闻畅, 刘宇, 顾进广. 基于注意力机制的双向长短时记忆网络模型突发事件演化关系抽取[J]. 计算机应用, 2019, 39(6):1646-1651.(WEN C, LIU Y, GU J G. Evolution relationship extraction of emergency based on attention-based bidirectional long short-term memory network model[J]. Journal of Computer Applications, 2019, 39(6):1646-1651.)
[6] NICKEL M, MURPHY K, TRESP V, et al. A review of relational machine learning for knowledge graphs[J]. Proceedings of the IEEE, 2016, 104(1):11-33.
[7] BORDES A, USUNIER N, GARCIA-DURÁN A. Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc., 2013:2787-2795.
[8] 吴运兵, 朱丹红, 廖祥文, 等. 路径张量分解的知识图谱推理算法[J]. 模式识别与人工智能, 2017, 30(5):473-480.(WU Y B, ZHU D H, LIAO X W, et al. Knowledge graph reasoning based on paths of tensor factorization[J]. Pattern Recognition and Artificial Intelligence, 2017, 30(5):473-480.)
[9] YANG B S, YIH W T, HE X D, et al. Embedding entities and relations for learning and inference in knowledge bases[EB/OL]. (2015-08-29)[2020-11-10]. https://arxiv.org/pdf/1412.6575.pdf.
[10] TROUILLON T, DANCE C R, GAUSSIER É, et al. Knowledge graph completion via complex tensor factorization[J]. Journal of Machine Learning Research, 2017, 18:1-38.
[11] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto, CA:AAAI Press, 2018:1811-1818.
[12] ZHAO L, QIU X, ZHANG Q, et al. Sequence labeling with deep gated dual path CNN[J]. Transactions on Audio, Speech, and Language Processing, 2019, 99:1-1.
[13] DAS R, NEELAKANTAN A, BELANGER D, et al. Chains of reasoning over entities, relations, and text using recurrent neural networks[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics(Volume 1, Long Papers). Stroudsburg, PA:Association for Computational Linguistics, 2017:132-141.
[14] LIN Y K, LIU Z Y, LUAN H B, et al. Modeling relation paths for representation learning of knowledge bases[C]//Proceeding of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2015:705-714.
[15] GARDNER M, TALUKDAR P P, KISIEL B, et al. Improving learning and inference in a large knowledge-base using latent syntactic cues[C]//Proceeding of the 2013 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2013:833-838.
[16] GARDNER M, MITCHELL T. Efficient and expressive knowledge base completion using subgraph feature extraction[C]//Proceeding of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA:Association for Computational Linguistics, 2015:1488-1498.
[17] WANG Q, MAO Z D, WANG B, et al. Knowledge graph embedding:a survey of approaches and applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(12):2724-2743.
[18] 杨瑞达, 林欣, 杨燕, 等. 基于混合增强智能的知识图谱推理技术研究[J]. 计算机应用与软件, 2019, 36(6):149-154. (YANG R D, LIN X, YANG Y, et al. Knowledge graph reasoning based on hybrid-augmented intelligence[J]. Computer Applications and Software, 2019, 36(6):149-154.)
[19] JIANG X T, WANG Q, QI B Y, et al. Attentive path combination for knowledge graph completion[C]//Proceedings of the 9th Asian Conference on Machine Learning. New York:JMLR. org, 2017:590-605.
[20] ZHOU P, SHI W, TIAN J, et al. Attention-based bidirectional long short-term memory networks for relation classification[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2:Short Papers). Stroudsburg. PA:Association for Computational Linguistics, 2016:207-212.

融合多跳关系路径信息的关系推理方法

Relationship reasoning method combining multi-hop relationship path information

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[2]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[3]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[4]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[5]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[6]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[7]	余敦辉, 万鹏, 王社. 基于企业知识图谱构建的实体关联查询系统[J]. 计算机应用, 2021, 41(9): 2510-2516.
[8]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[9]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[10]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[11]	田玲, 张谨川, 张晋豪, 周望涛, 周雪. 知识图谱综述——表示、构建、推理与知识超图理论[J]. 计算机应用, 2021, 41(8): 2161-2186.
[12]	党伟超, 李涛, 白尚旺, 高改梅, 刘春霞. 基于自注意力长短期记忆网络的Web软件系统实时剩余寿命预测方法[J]. 计算机应用, 2021, 41(8): 2346-2351.
[13]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[14]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[15]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.