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

TL;DR

This paper introduces SuperBorrow, a supervised method that leverages textual relation representations from co-occurring entity pairs to improve knowledge graph completion for entity pairs without direct textual mentions.

Contribution

It proposes a novel supervised borrowing approach, SuperBorrow, to represent relations between non-co-occurring entity pairs using textual data, enhancing existing KGE methods.

Findings

SuperBorrow improves link prediction performance across multiple KGE models.

The method effectively utilizes textual relation representations for non-mention entity pairs.

Experimental results demonstrate significant gains over prior approaches.

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 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.