Pith. sign in

REVIEW 1 cited by

LEMON: LanguagE ModeL for Negative Sampling of Knowledge Graph Embeddings

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.04703 v3 pith:WKUBCGVH submitted 2022-03-09 cs.AI cs.LG

classification cs.AIcs.LG
keywords knowledgenegativeentitiesgraphmodelstripleslearningapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Knowledge Graph Embedding models have become an important area of machine learning.Those models provide a latent representation of entities and relations in a knowledge graph which can then be used in downstream machine learning tasks such as link prediction. The learning process of such models can be performed by contrasting positive and negative triples. While all triples of a KG are considered positive, negative triples are usually not readily available. Therefore, the choice of the sampling method to obtain the negative triples play a crucial role in the performance and effectiveness of Knowledge Graph Embedding models. Most of the current methods fetch negative samples from a random distribution of entities in the underlying Knowledge Graph which also often includes meaningless triples. Other known methods use adversarial techniques or generative neural networks which consequently reduce the efficiency of the process. In this paper, we propose an approach for generating informative negative samples considering available complementary knowledge about entities. Particularly, Pre-trained Language Models are used to form neighborhood clusters by utilizing the distances between entities to obtain representations of symbolic entities via their textual information. Our comprehensive evaluations demonstrate the effectiveness of the proposed approach on benchmark Knowledge Graphs with textual information for the link prediction task.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Domain and Range Aware Synthetic Negatives Generation for Knowledge Graph Embedding Models

    cs.AI 2024-11 conditional novelty 4.0 of 10

    Mixing type-constrained and random negative sampling improves KGE link prediction on FB15k-237 and Hetionet for all four tested models, but gives near-zero or negative gains on WN18RR.

Pith tools