Learning to Borrow -- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion
This addresses a specific bottleneck in integrating text corpora with knowledge graphs for entities lacking direct textual mentions, offering an incremental improvement over prior work.
The paper tackled the problem of representing relations between entity pairs that do not co-occur in sentences for knowledge graph completion, proposing a supervised method called SuperBorrow that borrows lexicalised dependency paths from co-occurring pairs, resulting in improved link prediction performance for multiple KGE methods.
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 borrow LDPs from the entity pairs that co-occur in sentences in the corpus (i.e. with mention entity pairs) to represent entity pairs that do not co-occur in any sentence in the corpus (i.e. without mention entity pairs). We propose a supervised borrowing method, SuperBorrow, that learns to score the suitability of an LDP to represent a without-mention 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.