Hyper-relational KGs encode much more knowledge than triple KGs. We adopt recent advances in Graph ML and propose a GNN encoder for such graphs along with a new benchmark. — Knowledge graphs (KGs) are a cornerstone of modern NLP and AI applications — recent works include Question Answering, Entity & Relation Linking, Language Modeling, Information Extraction, and even playing text RPGs with Reinforcement Learning. Furthermore, KGs are already widely adopted in the industry, e.g., …
