A Three-stage Neuro-symbolic Recommendation Pipeline for Cultural Heritage Knowledge Graphs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kutt, Krzysztof, Sroka, Elżbieta, Ishchuk, Oleksandra, Miranda, Luiz do Valle
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917288458846208
author Kutt, Krzysztof
Sroka, Elżbieta
Ishchuk, Oleksandra
Miranda, Luiz do Valle
author_facet Kutt, Krzysztof
Sroka, Elżbieta
Ishchuk, Oleksandra
Miranda, Luiz do Valle
contents The growing volume of digital cultural heritage resources highlights the need for advanced recommendation methods capable of interpreting semantic relationships between heterogeneous data entities. This paper presents a complete methodology for implementing a hybrid recommendation pipeline integrating knowledge-graph embeddings, approximate nearest-neighbour search, and SPARQL-driven semantic filtering. The work is evaluated on the JUHMP (Jagiellonian University Heritage Metadata Portal) knowledge graph developed within the CHExRISH project, which at the time of experimentation contained ${\approx}3.2$M RDF triples describing people, events, objects, and historical relations affiliated with the Jagiellonian University (Kraków, PL). We evaluate four embedding families (TransE, ComplEx, ConvE, CompGCN) and perform hyperparameter selection for ComplEx and HNSW. Then, we present and evaluate the final three-stage neuro-symbolic recommender. Despite sparse and heterogeneous metadata, the approach produces useful and explainable recommendations, which were also proven with expert evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2602_19711
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Three-stage Neuro-symbolic Recommendation Pipeline for Cultural Heritage Knowledge Graphs
Kutt, Krzysztof
Sroka, Elżbieta
Ishchuk, Oleksandra
Miranda, Luiz do Valle
Information Retrieval
Digital Libraries
Human-Computer Interaction
The growing volume of digital cultural heritage resources highlights the need for advanced recommendation methods capable of interpreting semantic relationships between heterogeneous data entities. This paper presents a complete methodology for implementing a hybrid recommendation pipeline integrating knowledge-graph embeddings, approximate nearest-neighbour search, and SPARQL-driven semantic filtering. The work is evaluated on the JUHMP (Jagiellonian University Heritage Metadata Portal) knowledge graph developed within the CHExRISH project, which at the time of experimentation contained ${\approx}3.2$M RDF triples describing people, events, objects, and historical relations affiliated with the Jagiellonian University (Kraków, PL). We evaluate four embedding families (TransE, ComplEx, ConvE, CompGCN) and perform hyperparameter selection for ComplEx and HNSW. Then, we present and evaluate the final three-stage neuro-symbolic recommender. Despite sparse and heterogeneous metadata, the approach produces useful and explainable recommendations, which were also proven with expert evaluation.
title A Three-stage Neuro-symbolic Recommendation Pipeline for Cultural Heritage Knowledge Graphs
topic Information Retrieval
Digital Libraries
Human-Computer Interaction
url https://arxiv.org/abs/2602.19711