Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks

2019 ◽

Cited By ~ 1

Author(s):

Fan Xiong ◽

Jianliang Gao

Keyword(s):

State Of The Art ◽

The State ◽

New Method ◽

Knowledge Graph ◽

Convolutional Network ◽

Convolutional Networks ◽

Graph Alignment ◽

Abstract Graph ◽

Cross Lingual

Graph convolutional network (GCN) is a promising approach that has recently been used to resolve knowledge graph alignment. In this paper, we propose a new method to entity alignment for cross-lingual knowledge graph. In the method, we design a scheme of attribute embedding for GCN training. Furthermore, GCN model utilizes the attribute embedding and structure embedding to abstract graph features simultaneously. Our preliminary experiments show that the proposed method outperforms the state-of-the-art GCN-based method.

Download Full-text

Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6476 ◽

2020 ◽

Vol 34 (05) ◽

pp. 9354-9361

Author(s):

Kun Xu ◽

Linfeng Song ◽

Yansong Feng ◽

Yan Song ◽

Dong Yu

Keyword(s):

State Of The Art ◽

The Other ◽

Knowledge Graph ◽

Alignment Algorithm ◽

Graph Alignment ◽

Current State ◽

Alignment Model ◽

The Many ◽

The One ◽

Cross Lingual

Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local optimal match for each source entity. This decoding method may not only cause the “many-to-one” problem but also neglect the coordinated nature of this task, that is, each alignment decision may highly correlate to the other decisions. In this paper, we introduce two coordinated reasoning methods, i.e., the Easy-to-Hard decoding strategy and joint entity alignment algorithm. Specifically, the Easy-to-Hard strategy first retrieves the model-confident alignments from the predicted results and then incorporates them as additional knowledge to resolve the remaining model-uncertain alignments. To achieve this, we further propose an enhanced alignment model that is built on the current state-of-the-art baseline. In addition, to address the many-to-one problem, we propose to jointly predict entity alignments so that the one-to-one constraint can be naturally incorporated into the alignment prediction. Experimental results show that our model achieves the state-of-the-art performance and our reasoning methods can also significantly improve existing baselines.

Download Full-text

Adversarial Attack against Cross-lingual Knowledge Graph Alignment

10.18653/v1/2021.emnlp-main.432 ◽

2021 ◽

Author(s):

Zeru Zhang ◽

Zijie Zhang ◽

Yang Zhou ◽

Lingfei Wu ◽

Sixing Wu ◽

...

Keyword(s):

Knowledge Graph ◽

Graph Alignment ◽

Adversarial Attack ◽

Cross Lingual

Download Full-text

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network

10.18653/v1/p19-1304 ◽

2019 ◽

Cited By ~ 16

Author(s):

Kun Xu ◽

Liwei Wang ◽

Mo Yu ◽

Yansong Feng ◽

Yan Song ◽

...

Keyword(s):

Neural Network ◽

Graph Matching ◽

Knowledge Graph ◽

Graph Alignment ◽

Cross Lingual

Download Full-text

Feature Similarity Learning Enhanced Knowledge Graph-based Convolutional Networks for Recommendation

10.1109/iscipt53667.2021.00146 ◽

2021 ◽

Author(s):

Boya Shi ◽

Zhong Zheng ◽

Tao Tian ◽

Wanru Du

Keyword(s):

Knowledge Graph ◽

Similarity Learning ◽

Convolutional Networks ◽

Feature Similarity

Download Full-text

TheyBuyForYou platform and knowledge graph: Expanding horizons in public procurement with open linked data

Semantic Web ◽

10.3233/sw-210442 ◽

2021 ◽

pp. 1-27

Author(s):

Ahmet Soylu ◽

Oscar Corcho ◽

Brian Elvesæter ◽

Carlos Badenes-Olmedo ◽

Tom Blount ◽

...

Keyword(s):

Linked Data ◽

Public Procurement ◽

Open Data ◽

Knowledge Graph ◽

Multiple Sources ◽

The Public ◽

Cross Border ◽

Data Platform ◽

Document Search ◽

Cross Lingual

Public procurement is a large market affecting almost every organisation and individual; therefore, governments need to ensure its efficiency, transparency, and accountability, while creating healthy, competitive, and vibrant economies. In this context, open data initiatives and integration of data from multiple sources across national borders could transform the procurement market by such as lowering the barriers of entry for smaller suppliers and encouraging healthier competition, in particular by enabling cross-border bids. Increasingly more open data is published in the public sector; however, these are created and maintained in siloes and are not straightforward to reuse or maintain because of technical heterogeneity, lack of quality, insufficient metadata, or missing links to related domains. To this end, we developed an open linked data platform, called TheyBuyForYou, consisting of a set of modular APIs and ontologies to publish, curate, integrate, analyse, and visualise an EU-wide, cross-border, and cross-lingual procurement knowledge graph. We developed advanced tools and services on top of the knowledge graph for anomaly detection, cross-lingual document search, and data storytelling. This article describes the TheyBuyForYou platform and knowledge graph, reports their adoption by different stakeholders and challenges and experiences we went through while creating them, and demonstrates the usefulness of Semantic Web and Linked Data technologies for enhancing public procurement.

Download Full-text

A Multi -Role Graph Attention Network for Knowledge Graph Alignment

10.1109/ijcnn52387.2021.9533889 ◽

2021 ◽

Author(s):

Linyi Ding ◽

Weijie Yuan ◽

Kui Meng ◽

Gongshen Liu

Keyword(s):

Knowledge Graph ◽

Attention Network ◽

Graph Alignment

Download Full-text

Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/556 ◽

2018 ◽

Cited By ~ 29

Author(s):

Muhao Chen ◽

Yingtao Tian ◽

Kai-Wei Chang ◽

Steven Skiena ◽

Carlo Zaniolo

Keyword(s):

Experimental Results ◽

Knowledge Graph ◽

Semantic Representations ◽

Alignment Task ◽

Structured Knowledge ◽

Knowledge Graphs ◽

Cross Lingual ◽

Low Coverage

Multilingual knowledge graph (KG) embeddings provide latent semantic representations of entities and structured knowledge with cross-lingual inferences, which benefit various knowledge-driven cross-lingual NLP tasks. However, precisely learning such cross-lingual inferences is usually hindered by the low coverage of entity alignment in many KGs. Since many multilingual KGs also provide literal descriptions of entities, in this paper, we introduce an embedding-based approach which leverages a weakly aligned multilingual KG for semi-supervised cross-lingual learning using entity descriptions. Our approach performs co-training of two embedding models, i.e. a multilingual KG embedding model and a multilingual literal description embedding model. The models are trained on a large Wikipedia-based trilingual dataset where most entity alignment is unknown to training. Experimental results show that the performance of the proposed approach on the entity alignment task improves at each iteration of co-training, and eventually reaches a stage at which it significantly surpasses previous approaches. We also show that our approach has promising abilities for zero-shot entity alignment, and cross-lingual KG completion.

Download Full-text

Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i01.5354 ◽

2020 ◽

Vol 34 (01) ◽

pp. 222-229

Author(s):

Zequn Sun ◽

Chengming Wang ◽

Wei Hu ◽

Muhao Chen ◽

Jian Dai ◽

...

Keyword(s):

Neural Networks ◽

Attention Mechanism ◽

Knowledge Graph ◽

Neighborhood Information ◽

Graph Alignment ◽

Gating Mechanism ◽

Neighborhood Structures ◽

Knowledge Graphs ◽

End To End ◽

Graph Neural Networks

Graph neural networks (GNNs) have emerged as a powerful paradigm for embedding-based entity alignment due to their capability of identifying isomorphic subgraphs. However, in real knowledge graphs (KGs), the counterpart entities usually have non-isomorphic neighborhood structures, which easily causes GNNs to yield different representations for them. To tackle this problem, we propose a new KG alignment network, namely AliNet, aiming at mitigating the non-isomorphism of neighborhood structures in an end-to-end manner. As the direct neighbors of counterpart entities are usually dissimilar due to the schema heterogeneity, AliNet introduces distant neighbors to expand the overlap between their neighborhood structures. It employs an attention mechanism to highlight helpful distant neighbors and reduce noises. Then, it controls the aggregation of both direct and distant neighborhood information using a gating mechanism. We further propose a relation loss to refine entity representations. We perform thorough experiments with detailed ablation studies and analyses on five entity alignment datasets, demonstrating the effectiveness of AliNet.

Download Full-text