Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction
Adrian Kochsiek, Apoorv Saxena, Inderjeet Nair, Rainer Gemulla · 2023
We propose KGT5-context, a simple sequenceto-sequence model for link prediction (LP) in knowledge graphs (KG).Our work expands on KGT5, a recent LP model that exploits textual features of the KG, has small model size, and is scalable.To reach good predictive performance, however, KGT5 relies on an ensemble with a knowledge graph embedding model, which itself is excessively large and costly to use.In this short paper, we show empirically that adding contextual information-i.e., information about the direct neighborhood of the query entity-alleviates the need for a separate KGE model to obtain good performance.The resulting KGT5-context model is simple, reduces model size significantly, and obtains state-of-the-art performance in our experimental study.