Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer

TL;DR

This paper introduces KEnS, a framework that embeds multiple language-specific knowledge graphs into a shared space and uses ensemble inference to improve the accuracy of predicting missing facts, leveraging complementary knowledge across languages.

Contribution

KEnS is the first framework to perform ensemble knowledge transfer across multiple language-specific KGs using shared embedding space and ensemble techniques.

Findings

KEnS outperforms state-of-the-art methods on five real-world language-specific KGs.

Ensemble inference effectively combines predictions from multiple KGs.

Shared embedding space captures cross-lingual entity associations.

Abstract

Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base construction and reasoning, and it has been the subject of much research in recent works using KG embeddings. While existing KG embedding approaches mainly learn and predict facts within a single KG, a more plausible solution would benefit from the knowledge in multiple language-specific KGs, considering that different KGs have their own strengths and limitations on data quality and coverage. This is quite challenging, since the transfer of knowledge among multiple independently maintained KGs is often hindered by the insufficiency of alignment information and the inconsistency of described facts. In this paper, we propose KEnS, a novel framework for embedding learning and ensemble knowledge transfer across a number of language-specific KGs. KEnS embeds all KGs in a shared embedding space, where the association of entities is captured based on self-learning. Then, KEnS performs ensemble inference to combine prediction results from embeddings of multiple language-specific KGs, for which multiple ensemble techniques are investigated. Experiments on five real-world language-specific KGs show that KEnS consistently improves state-of-the-art methods on KG completion, via effectively identifying and leveraging complementary knowledge.