| Texto completo | |
| Autor(es): |
Ruschel, Andrey
;
Gusmao, Arthur Colombini
;
Cozman, Fabio Gagliardi
Número total de Autores: 3
|
| Tipo de documento: | Artigo Científico |
| Fonte: | INTERNATIONAL JOURNAL OF APPROXIMATE REASONING; v. 171, p. 25-pg., 2024-06-13. |
| Resumo | |
Completion of large-scale knowledge bases, such as DBPedia or Freebase, often relies on embedding models that turn symbolic relations into vector -based representations. Such embedding models are rather opaque to the human user. Research in interpretability has emphasized non -relational classifiers, such as deep neural networks, and has devoted less effort to opaque models extracted from relational structures, such as knowledge graph embeddings. We introduce techniques that produce explanations, expressed as logical rules, for predictions based on the embeddings of knowledge graphs. Algorithms build explanations out of paths in an input knowledge graph, searched through contextual and heuristic cues. (AU) | |
| Processo FAPESP: | 19/07665-4 - Centro de Inteligência Artificial |
| Beneficiário: | Fabio Gagliardi Cozman |
| Modalidade de apoio: | Auxílio à Pesquisa - Programa eScience e Data Science - Centros de Pesquisa em Engenharia |
| Processo FAPESP: | 17/19007-6 - Algoritmos de inferência e aprendizagem para programação lógica probabilística |
| Beneficiário: | Arthur Colombini Gusmão |
| Modalidade de apoio: | Bolsas no Brasil - Mestrado |