Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model

EMNLP/IJCNLP (1), pp. 2723-2732, 2019.

Cited by: 11|Bibtex|Views124|
EI
Keywords:
entity alignmentGraph Convolutional Networkembedding modelKnowledge GraphsGraph Neural NetworksMore(7+)
Weibo:
We propose a semi-supervised entity alignment method Knowledge Embedding model and Cross-Graph model that combines the knowledge embedding model and graph-based model

Abstract:

Entity alignment aims at integrating complementary knowledge graphs (KGs) from different sources or languages, which may benefit many knowledge-driven applications. It is challenging due to the heterogeneity of KGs and limited seed alignments. In this paper, we propose a semi-supervised entity alignment method by joint Knowledge Embedding...More

Code:

Data:

0
Introduction
Highlights
  • Many Knowledge Graphs (KGs) (e.g., DBpedia (Lehmann et al, 2015), YAGO (Rebele et al, 2016) and BabelNet (Navigli and Ponzetto, 2012)) have emerged to provide structural knowledge for different applications
  • We propose a semi-supervised entity alignment method by joint Knowledge Embedding model and Cross-Graph model (KECG), which combines the above two types of methods
  • Knowledge Embedding model and Cross-Graph model is significantly more effective than MTransE, JAPE, and Graph Convolutional Network-Align on all datasets, and slightly outperform AlignEA on small-scale datasets but greatly on large-scale datasets
  • AlignEA is the strongest one, which results from it using two margins to control the scores of triplets, making the Knowledge Graphs structure modeling based on triplets more accurate than others
  • We propose a semi-supervised entity alignment method Knowledge Embedding model and Cross-Graph model that combines the knowledge embedding model and graph-based model
  • Iteratively discovering new entity alignments based on the framework of Knowledge Embedding model and Cross-Graph model is another interesting direction
Methods
  • DBP15KZH−EN DBP15KJA−EN DBP15KFR−EN DWY100KWD DWY100KYG.
  • Hits@1 Hits@10 MRR Hits@1 Hits@10 MRR Hits@1 Hits@10 MRR Hits@1 Hits@10 MRR Hits@1 Hits@10 MRR MTransE JAPE.
  • KECG “*” denotes the unreported metrics in their papers.
  • The authors reproduced the results using their source code
Results
  • KECG propagates these features to unaligned entities, making the positions of the unaligned entities in the vector space very close to the corresponding entities
  • It reflects the importance of the global structural information of KGs. Compared with the graph-based model, KECG significantly outperforms GCN-Align regarding all metrics.
  • Compared with the graph-based model, KECG significantly outperforms GCN-Align regarding all metrics
  • It shows that involving the local relationships between entities can make entities more distinguishable, making the alignment more accurate
Conclusion
  • The authors propose a semi-supervised entity alignment method KECG that combines the knowledge embedding model and graph-based model.
  • The authors will extend the knowledge embedding model of KECG to other KG representation learning methods, such as TransD (Ji et al, 2015), to gain a stronger ability of modeling relationships.
  • Iteratively discovering new entity alignments based on the framework of KECG is another interesting direction
Summary
  • Introduction:

    Many Knowledge Graphs (KGs) (e.g., DBpedia (Lehmann et al, 2015), YAGO (Rebele et al, 2016) and BabelNet (Navigli and Ponzetto, 2012)) have emerged to provide structural knowledge for different applications.
  • KG-based models (Hao et al, 2016; Chen et al, 2017; Sun et al, 2017; Zhu et al, 2017; Sun et al, 2018; Chen et al, 2018) utilize existing KG representation learning methods to learn embeddings of entities and relations in different KGs, and align them into a unified vector space.
  • The authors use bold-face letters to denote the vector representations of the corresponding terms throughout the paper
  • Methods:

    DBP15KZH−EN DBP15KJA−EN DBP15KFR−EN DWY100KWD DWY100KYG.
  • Hits@1 Hits@10 MRR Hits@1 Hits@10 MRR Hits@1 Hits@10 MRR Hits@1 Hits@10 MRR Hits@1 Hits@10 MRR MTransE JAPE.
  • KECG “*” denotes the unreported metrics in their papers.
  • The authors reproduced the results using their source code
  • Results:

    KECG propagates these features to unaligned entities, making the positions of the unaligned entities in the vector space very close to the corresponding entities
  • It reflects the importance of the global structural information of KGs. Compared with the graph-based model, KECG significantly outperforms GCN-Align regarding all metrics.
  • Compared with the graph-based model, KECG significantly outperforms GCN-Align regarding all metrics
  • It shows that involving the local relationships between entities can make entities more distinguishable, making the alignment more accurate
  • Conclusion:

    The authors propose a semi-supervised entity alignment method KECG that combines the knowledge embedding model and graph-based model.
  • The authors will extend the knowledge embedding model of KECG to other KG representation learning methods, such as TransD (Ji et al, 2015), to gain a stronger ability of modeling relationships.
  • Iteratively discovering new entity alignments based on the framework of KECG is another interesting direction
Tables
  • Table1: Statistics of DBP15K and DWY100K
  • Table2: Results comparison on entity alignment(Results of Hits@1 and Hits@10 are percentage values)
Download tables as Excel
Related work
  • 5.1 KG Embedding

    Various KG embedding methods have shown effectiveness in modeling the semantic information of KGs. TransE (Bordes et al, 2013) is a milestone in learning embeddings for KGs, which interprets a relation as the translation from its head entity to its tail entity. Then it motivated several enhanced methods like TransR (Lin et al, 2015). In addition to them, non-translational methods also achieve satisfactory performances, such as RESCAL (Nickel et al, 2011), ConvE (Dettmers et al, 2018) and RotatE (Sun et al, 2019). Meanwhile, external information in KGs is fused to improve embedding (Wang and Li, 2016). More detailed KG embedding methods are summarized in (Wang et al, 2017).
Funding
  • This work is supported by National Key Research and Development Program of China (2017YFB1002101), NSFC key projects (U1736204, 6153301), a research fund by Alibaba, and THUNUS NExT Co-Lab
  • NExT++ research is supported by the National Research Foundation, Prime Minister’s Office, Singapore under its IRC@SG Funding Initiative
Reference
  • Antoine Bordes, Nicolas Usunier, Alberto GarciaDuran, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multirelational data. In NeurIPS.
    Google ScholarFindings
  • Joan Bruna, Wojciech Zaremba, Arthur Szlam, and Yann LeCun. 2014. Spectral networks and locally connected networks on graphs. In ICLR.
    Google ScholarFindings
  • Yixin Cao, Lei Hou, Juanzi Li, and Zhiyuan Liu. 2018. Neural collective entity linking. In COLING.
    Google ScholarLocate open access versionFindings
  • Muhao Chen, Yingtao Tian, Kai-Wei Chang, Steven Skiena, and Carlo Zaniolo. 2018. Co-training embeddings of knowledge graphs and entity descriptions for cross-lingual entity alignment. In IJCAI.
    Google ScholarFindings
  • Muhao Chen, Yingtao Tian, Mohan Yang, and Carlo Zaniolo. 2017. Multilingual knowledge graph embeddings for cross-lingual knowledge alignment. In IJCAI.
    Google ScholarFindings
  • Wanyun Cui, Yanghua Xiao, Haixun Wang, Yangqiu Song, Seung-won Hwang, and Wei Wang. 2017. Kbqa: learning question answering over qa corpora and knowledge bases. PVLDB.
    Google ScholarLocate open access versionFindings
  • Michael Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In NeurIPS.
    Google ScholarFindings
  • Tim Dettmers, Minervini Pasquale, Stenetorp Pontus, and Sebastian Riedel. 201Convolutional 2d knowledge graph embeddings. In AAAI.
    Google ScholarFindings
  • Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In NeurIPS.
    Google ScholarFindings
  • Xu Han, Zhiyuan Liu, and Maosong Sun. 2018. Neural knowledge acquisition via mutual attention between knowledge graph and text. In AAAI.
    Google ScholarFindings
  • Yanchao Hao, Yuanzhe Zhang, Shizhu He, Kang Liu, and Jun Zhao. 2016. A joint embedding method for entity alignment of knowledge bases. In CCKS.
    Google ScholarFindings
  • Wei Hu, Jianfeng Chen, and Yuzhong Qu. 2011. A self-training approach for resolving object coreference on the semantic web. In WWW.
    Google ScholarFindings
  • Guoliang Ji, Shizhu He, Liheng Xu, Kang Liu, and Jun Zhao. 2015. Knowledge graph embedding via dynamic mapping matrix. In ACL.
    Google ScholarFindings
  • Thomas N Kipf and Max Welling. 2017. Semisupervised classification with graph convolutional networks. In ICLR.
    Google ScholarFindings
  • Bhushan Kotnis and Vivi Nastase. 2017. Analysis of the impact of negative sampling on link prediction in knowledge graphs. arXiv preprint arXiv:1708.06816.
    Findings
  • Jens Lehmann, Robert Isele, Max Jakob, Anja Jentzsch, Dimitris Kontokostas, Pablo N Mendes, Sebastian Hellmann, Mohamed Morsey, Patrick Van Kleef, Soren Auer, et al. 2015. Dbpedia–a large-scale, multilingual knowledge base extracted from wikipedia. Semantic Web.
    Google ScholarFindings
  • Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, and Xuan Zhu. 2015. Learning entity and relation embeddings for knowledge graph completion. In AAAI.
    Google ScholarFindings
  • Andrew L Maas, Awni Y Hannun, and Andrew Y Ng. 2013. Rectifier nonlinearities improve neural network acoustic models. In ICML.
    Google ScholarFindings
  • Farzaneh Mahdisoltani, Joanna Biega, and Fabian M Suchanek. 2013. Yago3: A knowledge base from multilingual wikipedias. In CIDR.
    Google ScholarLocate open access versionFindings
  • Roberto Navigli and Simone Paolo Ponzetto. 2012. Babelnet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network. Artificial Intelligence.
    Google ScholarFindings
  • Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. 2011. A three-way model for collective learning on multi-relational data. In ICML.
    Google ScholarFindings
  • Thomas Rebele, Fabian Suchanek, Johannes Hoffart, Joanna Biega, Erdal Kuzey, and Gerhard Weikum. 2016. Yago: A multilingual knowledge base from wikipedia, wordnet, and geonames. In ISWC.
    Google ScholarFindings
  • John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. JMLR.
    Google ScholarLocate open access versionFindings
  • Zequn Sun, Wei Hu, and Chengkai Li. 2017. Cross-lingual entity alignment via joint attributepreserving embedding. In ISWC.
    Google ScholarFindings
  • Zequn Sun, Wei Hu, Qingheng Zhang, and Yuzhong Qu. 2018. Bootstrapping entity alignment with knowledge graph embedding. In IJCAI.
    Google ScholarFindings
  • Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. 2019. Rotate: Knowledge graph embedding by relational rotation in complex space. In ICLR.
    Google ScholarFindings
  • Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In NeurIPS.
    Google ScholarFindings
  • Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. In ICLR.
    Google ScholarFindings
  • Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. 2017. Knowledge graph embedding: A survey of approaches and applications. TKDE.
    Google ScholarLocate open access versionFindings
  • Zhichun Wang, Juanzi Li, and Jie Tang. 2013. Boosting cross-lingual knowledge linking via concept annotation. In IJCAI.
    Google ScholarFindings
  • Zhichun Wang, Qingsong Lv, Xiaohan Lan, and Yu Zhang. 2018. Cross-lingual knowledge graph alignment via graph convolutional networks. In EMNLP.
    Google ScholarFindings
  • Zhigang Wang and Juanzi Li. 2016. Text-enhanced representation learning for knowledge graph. In IJCAI.
    Google ScholarFindings
  • Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding entities and relations for learning and inference in knowledge bases. In ICLR.
    Google ScholarFindings
  • Hao Zhu, Ruobing Xie, Zhiyuan Liu, and Maosong Sun. 2017. Iterative entity alignment via joint knowledge embeddings. In IJCAI.
    Google ScholarFindings
Your rating :
0

 

Tags
Comments