Context-Guided Self-supervised Relation Embeddings

Hakami, Huda; Bollegala, Danushka

doi:10.1007/978-981-15-6168-9_6

Cited by 1 publication

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(1) considers the information in the head and tail entity embeddings independently as well as the interactions between their corresponding dimensions. These features for entity-pairs have been used successfully for representing semantic relations in prior work (Washio and Kato, 2018;Joshi et al, 2018;Hakami and Bollegala, 2019). The final output vector f (h, t; θ) of the MLP is treated as the representation of the entity-pair (h, t).…”

Section: Learn To Borrow Ldpsmentioning

confidence: 99%

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

Hakami¹,

Hakami²,

Mandya³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

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 cooccur 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, Su-perBorrow, 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.

show abstract

Section: Learn To Borrow Ldpsmentioning

confidence: 99%