Improving Cross-lingual Entity Alignment via Optimal Transport

Cross-lingual entity alignment identifies entity pairs that share the same meanings but locate in different language knowledge graphs (KGs). The study in this paper is to address two limitations that widely exist in current solutions: 1) the alignment loss functions defined at the entity level serve well the purpose of aligning labeled entities but fail to match the whole picture of labeled and unlabeled entities in different KGs; 2) the translation from one domain to the other has been considered (e.g., X to Y by M1 or Y to X by M2). However, the important duality of alignment between different KGs (X to Y by M1 and Y to X by M2) is ignored. We propose a novel entity alignment framework (OTEA), which dually optimizes the entitylevel loss and group-level loss via optimal transport theory. We also impose a regularizer on the dual translation matrices to mitigate the effect of noise during transformation. Extensive experimental results show that our model consistently outperforms the state-of-the-arts with significant improvements on alignment accuracy.

[1]  Nesime Tatbul,et al.  Proceedings of the VLDB Endowment , 2011 .

[2]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[3]  Zhichun Wang,et al.  Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks , 2018, EMNLP.

[4]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[5]  Feiping Nie,et al.  Efficient and Robust Feature Selection via Joint ℓ2, 1-Norms Minimization , 2010, NIPS.

[6]  Mohamed-Jalal Fadili,et al.  Wasserstein active contours , 2012, 2012 19th IEEE International Conference on Image Processing.

[7]  Markus Krötzsch,et al.  Wikidata , 2014, Commun. ACM.

[8]  Jack Xin,et al.  Minimization of ℓ1-2 for Compressed Sensing , 2015, SIAM J. Sci. Comput..

[9]  Samuel L. Smith,et al.  Offline bilingual word vectors, orthogonal transformations and the inverted softmax , 2017, ICLR.

[10]  Alessandro Rudi,et al.  Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance , 2018, NeurIPS.

[11]  Jason Weston,et al.  Translating Embeddings for Modeling Multi-relational Data , 2013, NIPS.

[12]  Zhiyuan Liu,et al.  Learning Entity and Relation Embeddings for Knowledge Graph Completion , 2015, AAAI.

[13]  Huajun Chen,et al.  The Semantic Web , 2011, Lecture Notes in Computer Science.

[14]  Juliana Freire,et al.  Multilingual Schema Matching for Wikipedia Infoboxes , 2011, Proc. VLDB Endow..

[15]  Claire Gardent,et al.  Improving Machine Learning Approaches to Coreference Resolution , 2002, ACL.

[16]  Marco Cuturi,et al.  Sinkhorn Distances: Lightspeed Computation of Optimal Transport , 2013, NIPS.

[17]  Fabian M. Suchanek,et al.  YAGO3: A Knowledge Base from Multilingual Wikipedias , 2015, CIDR.

[18]  Zhen Wang,et al.  Knowledge Graph Embedding by Translating on Hyperplanes , 2014, AAAI.

[19]  Wei Hu,et al.  Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding , 2017, SEMWEB.

[20]  Zhe Gan,et al.  Adversarial Text Generation via Feature-Mover's Distance , 2018, NeurIPS.

[21]  Gabriel Peyré,et al.  Computational Optimal Transport , 2018, Found. Trends Mach. Learn..

[22]  Wei Liu,et al.  Distilled Wasserstein Learning for Word Embedding and Topic Modeling , 2018, NeurIPS.

[23]  Jun Zhao,et al.  Knowledge Graph Embedding via Dynamic Mapping Matrix , 2015, ACL.

[24]  Wei Hu,et al.  Bootstrapping Entity Alignment with Knowledge Graph Embedding , 2018, IJCAI.

[25]  Markus Nentwig,et al.  A survey of current Link Discovery frameworks , 2016, Semantic Web.

[26]  Yuzhong Qu,et al.  A self-training approach for resolving object coreference on the semantic web , 2011, WWW.

[27]  C. Villani.  Optimal Transport: Old and New , 2008 .

[28]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[29]  Jianfeng Gao,et al.  Embedding Entities and Relations for Learning and Inference in Knowledge Bases , 2014, ICLR.

[30]  Zhiyuan Liu,et al.  Iterative Entity Alignment via Joint Knowledge Embeddings , 2017, IJCAI.

[31]  Carlo Zaniolo,et al.  Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment , 2016, IJCAI.

[32]  Yizhou Sun,et al.  Entity Matching across Heterogeneous Sources , 2015, KDD.

[33]  Steven Skiena,et al.  Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment , 2018, IJCAI.