English

Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer

Computation and Language 2020-10-09 v2 Artificial Intelligence Machine Learning

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.

Keywords

Cite

@article{arxiv.2010.03158,
  title  = {Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer},
  author = {Xuelu Chen and Muhao Chen and Changjun Fan and Ankith Uppunda and Yizhou Sun and Carlo Zaniolo},
  journal= {arXiv preprint arXiv:2010.03158},
  year   = {2020}
}

Comments

Findings of EMNLP 2020