Knowledge Base Completion
48 papers with code • 0 benchmarks • 1 datasets
Knowledge base completion is the task which automatically infers missing facts by reasoning about the information already present in the knowledge base. A knowledge base is a collection of relational facts, often represented in the form of "subject", "relation", "object"-triples.
The recent graph convolutional network (GCN) provides another way of learning graph node embedding by successfully utilizing graph connectivity structure.
Ranked #22 on Link Prediction on FB15k-237
In this paper, we propose multimodal knowledge base embeddings (MKBE) that use different neural encoders for this variety of observed data, and combine them with existing relational models to learn embeddings of the entities and multimodal data.
Additionally, we propose a new dataset for knowledge base completion constructed from Wikidata, larger than previous benchmarks by an order of magnitude, as a new reference for evaluating temporal and non-temporal link prediction methods.
Ranked #1 on Link Prediction on ICEWS14
Knowledge base completion (KBC) aims to predict missing information in a knowledge base. In this paper, we address the out-of-knowledge-base (OOKB) entity problem in KBC:how to answer queries concerning test entities not observed at training time.