计算机科学 ›› 2023, Vol. 50 ›› Issue (11): 234-240.doi: 10.11896/jsjkx.221000056
单晓欢, 赵雪, 陈廷伟
SHAN Xiaohuan, ZHAO Xue, CHEN Tingwei
摘要： 知识图谱作为大数据时代的人工智能,被广泛应用于诸多领域,然而知识图谱普遍存在不完备性及稀疏性等问题。知识补全作为知识获取的子任务,旨在通过知识库中已知三元组来预测缺失的链接。然而现有方法普遍忽略了实体类型信息联合邻域信息对提高知识补全准确性的辅助作用,同时还存在特征信息被紧密编码到目标函数,导致集成操作高度依赖训练过程等问题。为此,提出了一种基于贝叶斯规则的具有层次注意力的知识补全方法。首先将实体类型和邻域信息视为层次结构,按关系进行分组,并独立计算组内各类信息的注意力权重。然后将实体类型和邻域信息编码为先验概率,将实例信息编码为似然概率,且按照贝叶斯规则将二者进行组合。实验结果表明,所提方法在FB15k数据集上的MRR(Mean Reciprocal Rank)指标比ConvE提高14.4%,比TKRL提高10.7%;在FB15k-237数据集上的MRR指标比TACT提高了2.1%。在FB15k,FB15k-237和YAGO26K-906数据集上,其Hits@1达到了77.5%,73.8%和95.1%,证明了引入具有层次结构的类型信息和邻域信息能够为实体嵌入更丰富、准确的描述信息,进而提升知识补全的精度。
中图分类号:
| [1]HUANG X,ZHANG J,LI D,et al.Knowledge graph embedding based question answering[C]//Proceedings of the Twelfth ACM International Conference on Web Search and Data Mi-ning.2019:105-113. [2]WANG X,HE X,CAO Y,et al.Kgat:Knowledge graph attention network for recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Disco-very & Data Mining.2019:950-958. [3]KAPANIPATHI P,THOST V,PATEL S S,et al.Infusingknowledge into the textual entailment task using graph convolutional networks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:8074-8081. [4]WANG S,DU Z J,MENG X F.Research progress of large-scale knowledge graph completion technology[J].Chinese Science:Information Science,2020,50(4):551-575. [5]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of the Advances in Neural Information Processing Systems.2013:2787-2795. [6]YANG B,YIH W T,HE X,et al.Embedding entities and relations for learning and inference in knowledge bases[C]//Proceedings of the International Conference on Learning Representations.2015. [7]TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//Proceedings of the 33th International Conference on Machine Learning.2016:2071-2080. [8]SUN Z,DENG Z H,NIE J Y,et al.Rotate:Knowledge graph embedding by relational rotation in complex space[C]//Proceedings of the International Conference on Learning Representations.2019. [9]DETTMERS T,MINERVINI P,STENETROP P,et al.Convolutional 2dknowledge graph embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018:1811-1818. [10]WANG Z,ZHANG J,FENG J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2014:1112-1119. [11]LIN Y,LIU Z,SUN M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2015:2181-2187. [12]NICKEL M,TRESP V,KRIEGEL H P.A three-way model for collective learning on multi-relational data[C]//Proceedings of the International Conference on Machine Learning.2011:809-816. [13]WANG J,LI X N,LI G Y.Knowledge Graph Completion Algorithm Based on Adaptive Attention Mechanism[J].Computer Science,2022,49(7):204-211. [14]ZHANG S,TAY Y,YAO L,et al.Quaternion knowledge graph embeddings[C]//Proceedings of the Advances in Neural Information Processing Systems.2019:2731-2741. [15]XIE R,LIU Z,SUN M.Representation Learning of Knowledge Graphs with Hierarchical Types[C]//Proceedings of the International Joint Conference on Artificial Intelligence.2016:2965-2971. [16]MA S,DING J,JIA W,et al.TransT:Type-based multiple embedding representations for knowledge graph completion[C]//Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases.2017:717-733. [17]HAO J,CHEN M,YU W,et al.Universal representation lear-ning of knowledge bases by jointly embedding instances and ontological concepts[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mi-ning.2019:1709-1719. [18]ZHANG Z,CAI J,ZHANG Y,et al.Learning hierarchy-aware knowledge graph embeddings for link prediction[C]//Procee-dings of the Thirty-Fourth AAAI Conference on Artificial Intelligence.2020:3065-3072. [19]CHEN J,HE H,WU F,et al.Topology-Aware Correlations Between Relations for Inductive Link Prediction in Knowledge Graphs[C]//Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence.2021:6271-6278. [20]ZHANG Y,ZHANG X,WANG J,et al.Generalized RelationLearning with Semantic Correlation Awareness for Link Prediction[C]//Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence.2021:4679-4687. [21]WANG C,ZHOU X,PAN S,et al.Exploring Relational Semantics for Inductive Knowledge Graph Completion[C]//Procee-dings of the Thirty-Sixth AAAI Conference on Artificial Intelligence.2022. [22]CAO Z,XU Q,YANG Z,et al.Geometry Interaction Knowledge Graph Embeddings[C]//Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence.2022. [23]SCHLICHTKRULL M,KIPF T N,BLOEM P,et al.Modeling relational data with graph convolutional networks[C]//Proceedings of the Extended Semantic Web Conference.2018:593-607. [24]BANSAL T,JUAN D C,RAVI S,et al.A2n:Attending toneighbors for knowledge graph inference[C]//Proceedings of the Association for Computational Linguistics.2019:4387-4392. [25]NATHANI D,CHAUHAN J,SHARMA C,et al.Learning attention-based embeddings for relation prediction in knowledge graphs[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:4719-4723. [26]QIN X,SHEIKH N,REINWALD B,et al.Relation-aware graph attention model with adaptive self-adversarial training[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:5774-5782. [27]KINGMA D P,BA J L.Adam:A method forstochastic optimization[C]//Proceedings of the International Conference on Lear-ning Representations.2014. |
|
||
首页