Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment
This addresses the challenge of aligning entities across languages in knowledge graphs, which is crucial for cross-lingual NLP tasks, but is incremental as it builds on existing embedding methods.
The paper tackles the problem of low coverage in cross-lingual entity alignment in knowledge graphs by co-training embeddings from both the graph structure and entity descriptions, achieving significant performance improvements over previous approaches.
Multilingual knowledge graph (KG) embeddings provide latent semantic representations of entities and structured knowledge with cross-lingual inferences, which benefit various knowledge-driven cross-lingual NLP tasks. However, precisely learning such cross-lingual inferences is usually hindered by the low coverage of entity alignment in many KGs. Since many multilingual KGs also provide literal descriptions of entities, in this paper, we introduce an embedding-based approach which leverages a weakly aligned multilingual KG for semi-supervised cross-lingual learning using entity descriptions. Our approach performs co-training of two embedding models, i.e. a multilingual KG embedding model and a multilingual literal description embedding model. The models are trained on a large Wikipedia-based trilingual dataset where most entity alignment is unknown to training. Experimental results show that the performance of the proposed approach on the entity alignment task improves at each iteration of co-training, and eventually reaches a stage at which it significantly surpasses previous approaches. We also show that our approach has promising abilities for zero-shot entity alignment, and cross-lingual KG completion.