Paper accepted in Repl4NLP 2023: Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction

The paper “Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction” by Adrian Kochsiek, Apoorv Saxena, Inderjeet Nair, and Rainer Gemulla has been accepted at the 2023 Repl4NLP Workshop on Representation Learning for NLP, hosted by ACL 2023.

We propose KGT5-context, a simple sequence-to-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.