知识图谱复杂逻辑推理是知识图谱中的一项重要任务,其目的是根据给定的起始节点和逻辑表达式来推理出答案节点。先前的工作主要关注的是如何对实体、关系和查询进行建模,忽略了相似查询对当前查询的影响。因此,该文提出了一种相似查询的定义(称之为同构查询),并设计了一种基于同构查询的组件,它可以利用同构查询的特性,在推理的每一步缩短查询嵌入和答案嵌入之间的距离,在不改变原有复杂逻辑推理模型结构的基础上提升模型的性能。实验结果表明,该文提出的组件可以在不同的数据集上为各类不同的基线模型带来1.6%-3.3%的提升,证明了该方法的有效性与灵活性。
Abstract
Complex logical reasoning is a fundamental task in knowledge graph, which is to deduce the target entities from anchor entities and relations in query. However, previous approaches haven’t considered relevance among similar queries that can be helpful for inference. This paper designs homogeneous query revisor, a flexible component which can be added to current approaches without changing their structure and improve the performance of complex query answering based on the features of similar queries. The revisor can bridge the distance between query embedding and answer embedding in each reasoning step. The performance of this revisor on different data sets is 1.6%-3.3% higher than that of the baseline models, which demonstrates the flexibility and effectiveness of our approach.
关键词
知识图谱 /
复杂逻辑推理 /
同构查询
{{custom_keyword}} /
Key words
knowledge graph /
complex logical reasoning /
homogeneous query
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] SINGHAL A. Introducing the knowledge graph: things, not strings[EB/OL]. https://www.blog.google/products/search/introducing-knowledge-graph-things-not/[2012-05-16].
[2] QIAN R. Understand your world with bing[EB/OL]. https://blogs.bing.com/search/2013/03/21/understand-your-world-with-bing/[2013-03-21].
[3] YASUNAGA M, REN H Y, BOSSELUT A, et al. QA-GNN: Reasoning with language models and knowledge graphs for question answering[C] //Proceedings of the North American Chapter of the Association for Computational Linguistics, 2021: 535-546.
[4] BERANT J, CHOU A, FROSTIG R, et al. Semantic parsing on freebase from question-answer pairs[C]. //Proceedings of Empirical Methods in Natural Language Processing, 2013: 1533-1544.
[5] SPEER R, CHIN J,HAVASI C. Conceptnet 5.5: An open multilingual graph of general knowledge[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence, 2017: 4444-4451.
[6] BOLLACKER K D, EVANS C, PARITOSH P, et al. Freebase: A collaboratively created graph database for structuring human knowledge[C]//Proceedings of the SIGMOD Conference, 2008: 1247-1250.
[7] REN H, HU W,LESKOVEC J. Query2box: Reasoning over knowledge graphs in vector space using box embeddings[C]//Proceedings of the International Conference on Learning Representations, 2020.
[8] HAMILTON W L, BAJAJ P, ZITNIK M, et al. Embedding logical queries on knowledge graphs[C]//Proceedings of the Neural Information Processing Systems, 2018: 2030-2041.
[9] REN H Y, LESKOVEC J. Beta embeddings for multi-hop logical reasoning in knowledge graphs[C]//Proceedings of the 34th International Conference on Neural Information Processing Systems, 2020: 19716-19726.
[10] REITER R. On closed world data bases[M]//In Readings in Artificial Intelligence, Elsevier, 1981: 119-140.
[11] BORDES A, USUNIER N, GARCIA DURAN A, et al. Translating embeddings for modeling multi-relational data[C]//Proceedings of the Neural Information Processing Systems, 2013: 2787-2795.
[12] YANG B S, YIH W T, HE X D, et al. Embedding entities and relations for learning and inference in knowledge bases[C]//Proceedings of the International Conference on Learning Representations, 2015.
[13] TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[C]//Proceedings of the ICML, Workshop and Conference Proceedings, 2016: 2071-2080.
[14] 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 In International Conference on Learning Representations, 2019.
[15] ZHANG Z Q, CAI J Y, ZHANG Y D, et al. Learning hierarchy-aware knowledge graph embeddings for link prediction[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, 2020: 3065-3072.
[16] GUU K, MILLER J, LIANG P. Traversing knowledge graphs in vector space[C]//Proceedings of Empirical Methods in Natural Language Processing, 2015: 318-327.
[17] 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, 2017: 132-141.
[18] 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, 2015: 156-166.
[19] ARAKELYAN E, DAZA D, MINERVINI P, et al. Complex query answering with neural link predictor[C]//Proceedings of the International Conference on Learning Representations, 2021.
[20] DAZA D, COCHEZ M. Message passing query embedding[C]//Proceedings of the ICML Workshop - Graph Representation Learning and Beyond, 2020.
[21] LIU L H, DU B X, JI H, et al. Neural-answering logical queries on knowledge graphs[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021: 1087-1097.
[22] CHOUDHARY N, RAO N, KATARIYA S, et al. Probabilistic entity representation model for chain reasoning over knowledge graphs[C]//Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021.
[23] ZHANG Z Q, WANG J, CHEN J J, et al. Cone: Cone embeddings for multi-hop reasoning over knowledge graphs[C]//Proceedings of the 35th International Conference on Neural Information Processing Systems, 2021: 19172-19183.
[24] DAVEY B, PRIESTLEY H. Introduction to lattices and order[M]. London: Cambridge University Press, 1989.
[25] SCHLICHTKRULL R, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//Proceedings of the European Semantic Web Conference. 2018: 593-607.
[26] KiPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the International Conference on Learning Representations, 2017.
[27] CAI L, YAN B, MAI G C, et al. Transgcn: Coupling transformation assumptions with graph convolutional networks for link prediction[C]//Proceedings of the 10th International Conference on Knowledge Capture, 2019: 131-138.
[28] VASHISHTH S, SANYAL S, NITIN V, et al. Composition-based multi-relational graph convolutional networks[C]//Proceedings of the International Conference on Learning Representations, 2020.
[29] CARLSON A, BETTERIDGE J, KISIEL B, et al. Toward an architecture for never-ending language learning[C]//Proceedings of the 24th AAAI Conference on Artificial Intelligence, 2010: 1306-1313.
[30] LELAND M, JOHN H, NATHANIEL S, et al. UMAP: Uniform manifold approximation and projection for dimension reduction[J]. The Journal of Open Source Software, 2018, 3(29), 861-870.
[31] CHOUDHARY N, RAO N, KATARIYA S, et al. Self-supervised hyperboloid representations from logical queries over knowledge graphs[C]//Proceedings of the International World Wide Web Conference, 2021: 1373-1384.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(U1811463,62072069)
{{custom_fund}}
PDF(4405 KB)
