Learning to Borrow– Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion

Anonymous

Abstract: Prior work on integrating text corpora with knowledge graphs (KGs) to improve Knowledge Graph Embedding (KGE) have obtained good performance for entities that co-occur in sentences in text corpora. Such sentences (textual mentions of entity-pairs) are represented as Lexicalised Dependency Paths (LDPs) between two entities. However, it is not possible to represent relations between entities that do not co-occur in a single sentence using LDPs. In this paper, we propose and evaluate several methods to address this problem, where we \emph{borrow} LDPs from the entity pairs that co-occur in sentences in the corpus (i.e. \emph{with mentions} entity pairs) to represent entity pairs that do \emph{not} co-occur in any sentence in the corpus (i.e. \emph{without mention} entity pairs). We propose a supervised borrowing method, \emph{SuperBorrow}, that learns to score the suitability of an LDP to represent a without-mentions entity pair using pre-trained entity embeddings and contextualised LDP representations. Experimental results show that SuperBorrow improves the link prediction performance of multiple widely-used prior KGE methods such as TransE, DistMult, ComplEx and RotatE.

Paper Type: long