Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment

By Muhao Chen, Yingtao Tian, Mohan Yang, Carlo Zaniolo. 2016

626 citations recorded by the source corpus.

Many recent works have demonstrated the benefits of knowledge graph embeddings in completing monolingual knowledge graphs. Inasmuch as related knowledge bases are built in several different languages, achieving cross-lingual knowledge alignment will help people in constructing a coherent knowledge base, and assist machines in dealing with different expressions of entity relationships across diverse human languages. Unfortunately, achieving this highly desirable cross-lingual alignment by human labor is very costly and error-prone. Thus, we propose MTransE, a translation-based model for multilingual knowledge graph embeddings, to provide a simple and automated solution. By encoding entities and relations of each language in a separated embedding space, MTransE provides transitions for each embedding vector to its cross-lingual counterparts in other spaces, while preserving the functionalities of monolingual embeddings. We deploy three different techniques to represent cross-lingual transitions, namely axis calibration, translation vectors, and linear transformations, and derive five variants for MTransE using different loss functions. Our models can be trained on partially aligned graphs, where just a small portion of triples are aligned with their cross-lingual counterparts. The experiments on cross-lingual entity matching and triple-wise alignment verification show promising results, with some variants consistently outperforming others on different tasks. We also explore how MTransE preserves the key properties of its monolingual counterpart.

Subfields: Artificial Intelligence, Management Science and Operations Research

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

In Management Science and Operations Research

Citations in the corpus

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “[133] categorizes monolingual relations and uses linear transformation to learn cross-lingual alignment for entities and relations.”
Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs (2019, methodology): “Recently, embedding-based methods [ Hao et al. , 2016; Chen et al. , 2017; Sun et al. , 2017; Zhu et al. , 2017; Sun et al. , 2018; Wang et al. , 2018 ] have been proposed to address this issue.”
Knowledge Graph Completion: A Review (2020, methodology): “The bilinear SME model performs better than the linear model on the linked prediction task, but the former requires d times more parameters to learn than the latter [56], [77].”
Multi-Channel Graph Neural Network for Entity Alignment (2019, methodology): “Following the success of KG representation learning, recent work embeds entities in different KGs into a low-dimensional vector space with the help of seed alignments (Chen et al., 2017).”
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, background): “MTransE [125] firstly studies entity alignment in the multilingual scenario.”
Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs (2019, methodology): “(Section 3) (Guu et al., 2015; McCallum et al., 2017; Yang et al., 2017).”
Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks (2018, background): “Because we use the same datasets as in (Sun et al., 2017), the results of JE, MTransE, and JAPE are obtained from (Sun et al., 2017).”
A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, neutral): “Figure 2: Degree distributions and average degrees of two popular datasets DBP15K [80] and WK3L [10] used in current approaches.”
Iterative Entity Alignment via Joint Knowledge Embeddings (2017, methodology): “In Linear Transformation Model, we initialize matrix following [Chen et al., 2016].”
Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation (2019, methodology): “We compare with recent embedding-based entity alignment models: MTransE (Chen et al. 2017), IPTransE (Zhu et al. 2017), JAPE (Sun, Hu, and Li 2017), AlignE (Sun et al. 2018), GCN-Align (Wang et al. 2018), SEA (Pei et al. 2019), RSN (Guo, Sun, and Hu 2019) and MuGNN (Cao et al. 2019).”
Entity Alignment between Knowledge Graphs Using Attribute Embeddings (2019, methodology): “To address this problem, Chen et al. (2017a; 2017b) and Zhu et al. (2017) learn an embedding space for each KG separately and propose to use a transition matrix to map the embedding space from one KG to the other.”
Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding (2017, methodology): “ibute triples contribute to a signiﬁcant portion of the datasets. 4 https://www.tensorflow.org/ 5 https://github.com/nju-websoft/JAPE 4.2 Comparative Approaches As aforementioned, JE [11] and MTransE [5] are two representative embeddingbased methods for entity alignment. In our experiments, we used ”
A Survey on Application of Knowledge Graph (2020, background): “The work [57] suggests that KGs can be applied to machine translation and this insight is supported by the research work [58] which contribute to aligning entities across languages by generates multilingual knowledge graph embeddings.”