CoDEx comprises a set of knowledge graph completion datasets extracted from Wikidata and Wikipedia that improve upon existing knowledge graph completion benchmarks in scope and level of difficulty. CoDEx comprises three knowledge graphs varying in size and structure, multilingual descriptions of entities and relations, and tens of thousands of hard negative triples that are plausible but verified
4 PAPERS • 1 BENCHMARK
3 PAPERS • 1 BENCHMARK
…The dataset is used for the Knowledge Graph Completion and Entity Alignment task. DPB-5L (French) is a subset of DPB-5L with French KG.
…The dataset is used for the Knowledge Graph Completion and Entity Alignment task. DPB-5L (Japanese) is a subset of DPB-5L with Japanese KG.
0 PAPER • NO BENCHMARKS YET
…The dataset is used for the Knowledge Graph Completion and Entity Alignment task. DPB-5L (Spanish) is a subset of DPB-5L with Spanish KG.
1 PAPER • NO BENCHMARKS YET
…The dataset is used for the Knowledge Graph Completion and Entity Alignment task. DPB-5L (English) is a subset of DPB-5L with English KG.
…The dataset is used for the Knowledge Graph Completion and Entity Alignment task. DPB-5L (Greek) is a subset of DPB-5L with Greek KG.
This dataset is a Wikipedia dump, split by relations to perform Few-Shot Knowledge Graph Completion.
15 PAPERS • NO BENCHMARKS YET
InferWiki is a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns.
4 PAPERS • NO BENCHMARKS YET