Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment

TL;DR

This paper introduces MTransE, a translation-based model for multilingual knowledge graph embeddings that enables automated cross-lingual knowledge alignment, improving the coherence of multilingual knowledge bases with minimal manual effort.

Contribution

MTransE provides a novel, automated approach for cross-lingual knowledge graph alignment by encoding entities in separate spaces and modeling transitions between them, with multiple techniques and variants.

Findings

MTransE achieves promising results in cross-lingual entity matching.

The model outperforms some variants in triple-wise alignment verification.

It effectively preserves monolingual embedding properties.

Abstract

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 crosslingual alignment by human labor is very costly and errorprone. 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 TransE.