Do Embeddings Actually Capture Knowledge Graph Semantics?

Jain, N. K.; Kalo, Jan-Christoph; Balke, Wolf‐Tilo; Krestel, Ralf

doi:10.1007/978-3-030-77385-4_9

Cited by 34 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…pyRDF2Vec was used as one of the data mining techniques during evaluation. In [10], pyRDF2Vec among many other embedding techniques, has been compared to non-embedding methods to better understand their semantic capabilities. In Sousa et al [20] pyRDF2Vec is used to tailor aspect-oriented semantic similarity measures to fit a particular view on biological similarity or relatedness in protein-protein, protein function similarity, protein sequence similarity and phenotype-based gene similarity tasks.…”

Section: Package Usagementioning

confidence: 99%

pyRDF2Vec: A Python Implementation and Extension of RDF2Vec

Vandewiele¹,

Steenwinckel²,

Agozzino³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper introduces pyRDF2Vec 1 , a Python software package that reimplements the well-known RDF2Vec algorithm along with several of its extensions. By making the algorithm available in the most popular data science language, and by bundling all extensions into a single place, the use of RDF2Vec is simplified for data scientists. The package is released under a MIT license and structured in such a way to foster further research into sampling, walking, and embedding strategies, which are vital components of the RDF2Vec algorithm. Several optimisations have been implemented in pyRDF2Vec that allow for more efficient walk extraction than the original algorithm. Furthermore, best practices in terms of code styling, testing, and documentation were applied such that the package is future-proof as well as to facilitate external contributions.

show abstract

Section: Package Usagementioning

confidence: 99%

pyRDF2Vec: A Python Implementation and Extension of RDF2Vec

Vandewiele¹,

Steenwinckel²,

Agozzino³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Graph neural networks (GNN) have been used to represent KB facts to inform ED predictions (Sevgili et al, 2019;Ma et al, 2021). These approaches can potentially access the information in all KB facts, but are reliant on the quality of the graph embeddings, which may struggle to represent many basic semantics (Jain et al, 2021) particularly for unpopular entities (Mohamed et al, 2020).…”

Section: Ed With Knowledge Graph Embeddingsmentioning

confidence: 99%

Improving Entity Disambiguation by Reasoning over a Knowledge Base

Ayoola¹,

Fisher²,

Pierleoni³

2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Recent work in entity disambiguation (ED) has typically neglected structured knowledge base (KB) facts, and instead relied on a limited subset of KB information, such as entity descriptions or types. This limits the range of contexts in which entities can be disambiguated. To allow the use of all KB facts, as well as descriptions and types, we introduce an ED model which links entities by reasoning over a symbolic knowledge base in a fully differentiable fashion. Our model surpasses state-of-the-art baselines on six well-established ED datasets by 1.3 F1 on average. By allowing access to all KB information, our model is less reliant on popularity-based entity priors, and improves performance on the challenging ShadowLink dataset (which emphasises infrequent and ambiguous entities) by 12.7 F1.

show abstract

“…Most popular knowledge graph datasets assume only one entity type (one vertex in Q) with a collection of relations mapping this type to itself. This typing scheme is often chosen for convenience and may deserve further consideration if one wishes to embed hierarchical, type-specific representational biases within knowledge graph embeddings [19]. We hint here at an alternative category-theoretic expression of the information contained in a knowledge graph and its schema.…”

Section: Knowledge Graph Embedding As Sheaf Learningmentioning

confidence: 99%

Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding

Gebhart¹,

Hansen²,

Sauseng³

2021

Preprint

View full text Add to dashboard Cite

Knowledge graph embedding involves learning representations of entities-the vertices of the graph-and relations-the edges of the graph-such that the resulting representations encode the known factual information represented by the knowledge graph are internally consistent and can be used in the inference of new relations. We show that knowledge graph embedding is naturally expressed in the topological and categorical language of cellular sheaves: learning a knowledge graph embedding corresponds to learning a knowledge sheaf over the graph, subject to certain constraints. In addition to providing a generalized framework for reasoning about knowledge graph embedding models, this sheaf-theoretic perspective admits the expression of a broad class of prior constraints on embeddings and offers novel inferential capabilities. We leverage the recently developed spectral theory of sheaf Laplacians to understand the local and global consistency of embeddings and develop new methods for reasoning over composite relations through harmonic extension with respect to the sheaf Laplacian. We then implement these ideas to highlight the benefits of the extensions inspired by this new perspective.Preprint. Under review.

show abstract

Do Embeddings Actually Capture Knowledge Graph Semantics?

Cited by 34 publications

References 24 publications

pyRDF2Vec: A Python Implementation and Extension of RDF2Vec

pyRDF2Vec: A Python Implementation and Extension of RDF2Vec

Improving Entity Disambiguation by Reasoning over a Knowledge Base

Knowledge Sheaves: A Sheaf-Theoretic Framework for Knowledge Graph Embedding

Contact Info

Product

Resources

About