Embedding based Link Prediction for Knowledge Graph Completion

This thesis proposes a novel Knowledge Graph (KG) embedding model for Link Prediction (LP) for Knowledge Graph Completion (KGC). The missing links in a KG are predicted based on the existing contextual information as well as textual entity descriptions. The model outperforms the state-of-the-art (SOTA) model DKRL for FB15k and FB15k-237 datasets