OERL: Enhanced Representation Learning via Open Knowledge Graphs

The sparseness and incompleteness of knowledge graphs (KGs) trigger considerable interest in enhancing the representation learning with external corpora. However, the difficulty of aligning entities and relations with external corpora leads to inferior performance improvement. Open knowledge graphs (OKGs) consist of entity-mentions and relation-mentions that are represented by noncanonicalized freeform phrases, which generally do not rely on the specification of ontology schema. The roughness of the nonontological construction method leads to a specific characteristic of OKGs: diversity, where multiple entity-mentions (or relation-mentions) have the same meaning but different expressions. The diversity of OKGs can provide potential textual and structural features for the representation learning of KGs. We speculate that leveraging OKGs to enhance the representation learning of KGs can be more effective than using pure text or pure structure corpora. In this paper, we propose a new OERL, Open knowledge graph Enhanced Representation Learning of KGs. OERL automatically extracts textual and structural connections between KGs and OKGs, models and transfers refined profitable features to enhance the representation learning of KGs. The strong performance improvement and exhaustive experimental analysis prove the superiority of OERL over state-of-the-art baselines.

Automated summary

In this paper, a new method called Open knowledge graph Enhanced Representation Learning of KGs (OERL) is proposed to address the sparseness and incompleteness of knowledge graphs. OERL extracts textual and structural connections between knowledge graphs and open knowledge graphs to enhance the representation learning. Experimental results demonstrate that OERL outperforms state-of-the-art baselines.