CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge

In this paper, we propose , a knowledge graph embedding (KGE) toolkit, which aims to represent the multi-source and heterogeneous knowledge. For multi-source knowledge, unlike existing methods that mainly focus on entity-centric world knowledge, CogKGE also supports the representations of eventcentric world knowledge, commonsense knowledge and linguistic knowledge. For heterogeneous knowledge, besides structured triple facts, CogKGE leverages additional unstructured information, such as text descriptions, node types and temporal information, to enhance the meaning of embeddings. Moreover, CogKGE aims to provide a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks. As a research framework, CogKGE consists of five parts, including core, data, model, knowledge and adapter module. As a knowledge discovery toolkit, CogKGE provides pretrained embedders to discover new facts, cluster entities and check facts. Furthermore, we construct two new benchmark datasets for further research on multi-source heterogeneous KGE tasks: EventKG240K and CogNet360K. We also release an online system 1 to discover knowledge visually. Source code, datasets and pre-trained embeddings are publicly available at GitHub 2 , with a short instruction video 3 .