Aligning Cross-Lingual Entities with Multi-Aspect Information

By Hsiu-Wei Yang, Yanyan Zou, Peng Shi, Wei Dang Lu, Jimmy J. Lin, Xu Sun. 2019

185 citations recorded by the source corpus.

Multilingual knowledge graphs (KGs), such as YAGO and DBpedia, represent entities in different languages. The task of cross-lingual entity alignment is to match entities in a source language with their counterparts in target languages. In this work, we investigate embedding-based approaches to encode entities from multilingual KGs into the same vector space, where equivalent entities are close to each other. Specifically, we apply graph convolutional networks (GCNs) to combine multi-aspect information of entities, including topological connections, relations, and attributes of entities, to learn entity embeddings. To exploit the literal descriptions of entities expressed in different languages, we propose two uses of a pretrained multilingual BERT model to bridge cross-lingual gaps. We further propose two strategies to integrate GCN-based and BERT-based modules to boost performance. Extensive experiments on two benchmark datasets demonstrate that our method significantly outperforms existing systems.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xindong Wu
2. Wei Dang Lu
3. Hao Peng
4. Lingfeng Zhong
5. Guoshun Nan
6. Qian Li
7. Jia Wu
8. Zhijiang Guo

Citations in the corpus

• A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, unknown): “d I is an identity matrix. D^ is the diagonal degree matrix of A^. W is the learnable weight matrix. ˙() is the activation function such as tanh( 2). Attribute embedding is used by several approaches [9, 28, 72, 77, 81, 83, 85, 87, 90] to enhance the similarity measure of entities. There are two way”
• A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, background): “[290] leverage a bag-of-words model to learn the contextual embeddings of attributes.”
• Reasoning with Latent Structure Refinement for Document-Level Relation Extraction (2020, methodology): “Graph neural networks have been widely used in different tasks to perform multi-hop reasoning (Song et al., 2018a; Yang et al., 2019; Tu et al., 2019; Lin et al., 2019), as they are able to effectively collect relevant evidence based on an information aggregation scheme.”