Knowledge Graph Completion Method Based on Multi-semantic Relation Embedding

doi:10.3778/j.issn.1673-9418.2205085

Abstract

Abstract: The knowledge graph completion method based on knowledge representation transforms entities and relationships into distributed representation, and completes missing relation by vector calculation. The existing knowledge graph representation model regards the relationship as a single vector and loses part of the relationship semantics. The traditional relational multi-semantic segmentation model is difficult to be applied in large-scale knowledge completion because of many parameters and high time consumption. In this paper, a relationship completion method of knowledge graph based on multi-semantic relationship embedding (MSRE) is proposed. The relationship angle vector is inversely calculated in complex domain space. And the semantic component cluster of each relationship is constructed based on Mean-Shift algorithm. The RotatE score function is optimized to obtain the most appropriate score of relational semantic component in the cluster. This method not only expands the relational representation, but also ensures the uniqueness in triplet operation. Experimental results of link prediction and triple classification on public datasets FB15K-237 and WN18RR show that this method can mine the potential semantics of relationships, maintain low time complexity, and improve the performance compared with mainstream models in most indicators.

Key words: knowledge graph, relation multiple semantics, relation embedding, clustering

摘要： 基于知识表示的知识图谱补全方法将实体与关系转化为分布式向量，通过向量计算补全缺失关系。现有的知识表示模型将关系看作单一向量，损失了部分关系语义。而传统关系多语义细分模型由于参数较多，时耗较大难以在大规模知识图谱上应用。提出了一种多语义关系嵌入的知识图谱补全方法（MSRE），在复数域空间中反向计算关系角度向量，基于Mean-Shift构建各关系的语义分量簇，优化RotatE得分函数为语义分量簇中最恰当的关系语义分量得分。该方法在扩充关系表示的同时，保证了三元组运算中的唯一性。在公开数据集FB15K-237、WN18RR上的链路预测和三元组分类的实验结果表明，该方法可以挖掘关系的潜在语义，保持较低的时间复杂度，且在多数指标上相较于主流模型有一定的性能提升。

关键词: 知识图谱, 关系多语义, 关系嵌入, 聚类

YIN Hua, XIAO Shiran, CHEN Zhiquan, HU Zhensheng, LONG Yongchao. Knowledge Graph Completion Method Based on Multi-semantic Relation Embedding[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(2): 467-477.

尹华, 肖石冉, 陈智全, 胡振生, 龙泳潮. 多语义关系嵌入的知识图谱补全方法[J]. 计算机科学与探索, 2023, 17(2): 467-477.

References

[1] REINANDA R, MEIJ E, RIJKE M D. Knowledge graphs: an information retrieval perspective[J]. Foundations and Trends in Information Retrieval, 2020, 14(4): 1-158.
[2] ZHOU S J, DAI X J, CHEN H K, et al. Interactive recom-mender system via knowledge graphenhanced reinforce-ment learning[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 179-188.
[3] ZHENG W, YIN L, CHEN X, et al. Knowledge base graph embedding module design for visual question answering model[J]. Pattern Recognition, 2021(2): 108-153.
[4] WEST R, GABRILOVICH E, MURPHY K, et al. Knowledge base completion via search-based question answering[C]//Proceedings of the 23rd International World Wide Web Conference, Seoul, Apr 7-11, 2014. New York: ACM, 2014: 515-526.
[5] MIN B, GRISHMAN R, WAN L, et al. Distant supervision for relation extraction with an incomplete knowledge base[C]//Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Atlanta, Jun 9-14, 2013. Stroudsburg: ACL, 2013: 777-782.
[6] CARLSON A, BETTERIDGE J, KISIEL B, et al. Toward an architecture for never-ending language learning[C]//Pro-ceedings of the 24th AAAI Conference on Artificial Intelli-gence, Atlanta, Jul 11-15, 2010. Menlo Park: AAAI, 2010: 1306-1313.
[7] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Tran-slating embeddings for modeling multi-relational data[C]//Proceedings of the Annual Conference on Neural Informa-tion Processing Systems 2013, Lake Tahoe, Dec 5-8, 2013. Red Hook: Curran Associates, 2013: 2787-2795.
[8] SOCHER R, CHEN D, MANNING C D, et al. Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of the Annual Conference on Neural Infor-mation Processing Systems 2013, Lake Tahoe, Dec 5-8, 2013. Red Hook: Curran Associates, 2013: 926-934.
[9] HAN X P, SUN L. Context-sensitive inference rule discovery: a graph-based method[C]//Proceedings of the 26th Interna-tional Conference on Computational Linguistics: Technical Papers, Osaka, Dec 11-16, 2016. Stroudsburg: ACL, 2016: 2902-2911.
[10] SUN Z Q, DENG Z H, NIE J Y, et al. RotatE: knowledge graph embedding by relational rotation in complex space[C]//Proceedings of the 7th International Conference on Learning Representations, New Orleans, May 6-9, 2019: 1-18.
[11] NICKEL M, TRESP V, KRIEGEL H P. A three-way model for collective learning on multi-relational data[C]//Procee-dings of the 28th International Conference on Machine Learning, Bellevue, Jun 28-Jul 2, 2011. Madison: Omni Press, 2011: 809-816.
[12] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[C]//Pro-ceedings of the 32nd AAAI Conference on Artificial Intel-ligence, the 30th Innovative Applications of Artificial In-telligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 1811-1818.
[13] NICKEL M, KIELA D. Poincaré embeddings for learning hierarchical representations[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2017, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 6338-6347.
[14] BALAZEVIC I, ALLEN C, HOSPEDALES T. Multi-relational poincaré graph embeddings[C]//Proceedings of the Annual Conference on Neural Information Processing Systems 2019, Vancouver, Dec 8-14, 2019: 4465-4475.
[15] XIAO H, HUANG M, ZHU X. TransG: a generative model for knowledge graph embedding[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Aug 7-12, 2016. Stroudsburg: ACL, 2016: 2316-2325.
[16] 刘知远, 孙茂松, 林衍凯, 等. 知识表示学习研究进展[J]. 计算机研究与发展, 2016, 53(2): 247-261.
LIU Z Y, SUN M S, LIN Y K, et al. Knowledge represen-tation learning: a review[J]. Journal of Computer Research and Development, 2016, 53(2): 247-261.
[17] NEELAKANTAN A, ROTH B, MCCALLUM A. Com-positional vector space models for knowledge base in-ference[C]//Proceedings of the 2015 AAAI Spring Sym-posia, Palo Alto, Mar 22-25, 2015. Menlo Park: AAAI, 2015: 1-4.
[18] XIONG W H, HOANG T, WANG W Y. DeepPath: a rein-forcement learning method for knowledge graph reasoning[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Sep 9-11, 2017. Stroudsburg: ACL, 2017: 564-573.
[19] ZHANG W, PAUDEL B, WANG L, et al. Iteratively lear-ning embeddings and rules for knowledge graph reasoning[C]//Proceedings of the 2019 World Wide Web Conference, San Francisco, May 13-17, 2019. New York: ACM, 2019: 2366-2377.
[20] XIONG W H, YU M, CHANG S Y, et al. One-shot rela-tional learning for knowledge graphs[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Oct 31-Nov 4, 2018. Stroud-sburg: ACL, 2018: 1980-1990.
[21] YANG B, YIH S W, HE X, et al. Embedding entities and relations for learning and inference in knowledge bases[C]//Proceedings of the 2015 International Conference on Learning Representations, San Diego, May 7-9, 2015: 1-12.
[22] VU T, NGUYEN T D, NGUYEN D Q, et al. A capsule net-work-based embedding model for knowledge graph comple-tion and search personalization[C]//Proceedings of the 2019 Conference of the North American Chapter of the Associa-tion for Computational Linguistics: Human Language Tech-nologies, Minneapolis, Jun 2-7, 2019. Menlo Park: AAAI, 2019: 2180-2189.
[23] WANG Z, ZHANG J, FENG J, et al. Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence, Québec City, Jul 27-31, 2014. Menlo Park: AAAI, 2014: 1112-1119.
[24] LIN Y, LIU Z, SUN M, et al. Learning entity and relation embeddings for knowledge graph completion[C]//Procee-dings of the 29th AAAI Conference on Artificial Intelli-gence, Austin, Jan 25-30, 2015. Menlo Park: AAAI, 2015: 2181-2187.
[25] JI G L, HE S Z, XU L H, et al. Knowledge graph embed-ding via dynamic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Beijing, Jul 26-31, 2015. Menlo Park: AAAI, 2015: 687-696.
[26] HAN X, HUANG M, YU H, et al. TransG: a generative mix-ture model for knowledge graph embedding[J]. arXiv:1509. 05488, 2015.
[27] BOLLACKER K D, EVANS C, PARITOSH P K, et al. Free-base: a collaboratively created graph database for structu-ring human knowledge[C]//Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, Vancouver, Jun 10-12, 2008. New York: ACM, 2008: 1247-1250.
[28] 陈小辉, 奚庆港. 基于DBSCAN的自适应聚类算法的研究与实现[J]. 淮阴师范学院学报(自然科学版), 2021, 20(3): 228-234.
CHEN X H, XI Q G. Research and implementation of adaptive clustering algorithm based on DBSCAN[J]. Jour-nal of Huaiyin Teachers College (Natural Science Edition), 2021, 20(3): 228-234.
[29] 张晨阳, 黄腾, 吴壮壮. 基于K-Means聚类与深度学习的RGB-D SLAM算法[J]. 计算机工程, 2022, 48(1): 236-244.
ZHANG C Y, HUANG T, WU Z Z. RGB-D SLAM algori-thm based on K-means clustering and deep learning[J]. Com-puter Engineering, 2022, 48(1): 236-244.
[30] MILLER G A. WordNet: a lexical database for English[J]. Communications of the ACM, 1995, 38(11): 39-41.
[31] BORDES A, GLOROT X, WESTON J, et al. A semantic matching energy function for learning with multi-relational data[J]. Machine Learning, 2014, 94(2): 233-259.