TY - GEN
T1 - Enhancing Entity Alignment Between Wikidata and ArtGraph Using LLMs
AU - Lippolis, Ana Sofia
AU - Klironomos, Antonis
AU - Milon-Flores, Daniela F.
AU - Zheng, Heng
AU - Jouglar, Alexane
AU - Norouzi, Ebrahim
AU - Hogan, Aidan
N1 - Publisher Copyright:
© 2023 Copyright for this paper by its authors.
PY - 2023/11/3
Y1 - 2023/11/3
N2 - Knowledge graphs (KGs) are used in a wide variety of applications, including within the cultural heritage domain. An important prerequisite of such applications is the quality and completeness of the data. Using a single KG might not be enough to fulfill this requirement. The absence of connections between KGs complicates taking advantage of the complementary data they can provide. This paper focuses on the Wikidata and A rtG raph KGs, which exhibit gaps in content that can be filled by enriching one with data from the other. Entity alignment can help to combine data from KGs by connecting entities that refer to the same real-world entities. However, entity alignment in art-domain knowledge graphs remains under-explored. In the pursuit of entity alignment between A rtG raph and Wikidata, a hybrid approach is proposed. The first part, which we call WES (Wikidata Entity Search), utilizes traditional Wikidata SPARQL queries and is followed by a supplementary sequence-to-sequence large language model (LLM) pipeline that we denote as pArtLink. The combined approach successfully aligned artworks and artists, with WES identifying entities for 14,982 artworks and 2,029 artists, and pArtLink further aligning 76 additional artists, thus enhancing the alignment process beyond WES’ capabilities.
AB - Knowledge graphs (KGs) are used in a wide variety of applications, including within the cultural heritage domain. An important prerequisite of such applications is the quality and completeness of the data. Using a single KG might not be enough to fulfill this requirement. The absence of connections between KGs complicates taking advantage of the complementary data they can provide. This paper focuses on the Wikidata and A rtG raph KGs, which exhibit gaps in content that can be filled by enriching one with data from the other. Entity alignment can help to combine data from KGs by connecting entities that refer to the same real-world entities. However, entity alignment in art-domain knowledge graphs remains under-explored. In the pursuit of entity alignment between A rtG raph and Wikidata, a hybrid approach is proposed. The first part, which we call WES (Wikidata Entity Search), utilizes traditional Wikidata SPARQL queries and is followed by a supplementary sequence-to-sequence large language model (LLM) pipeline that we denote as pArtLink. The combined approach successfully aligned artworks and artists, with WES identifying entities for 14,982 artworks and 2,029 artists, and pArtLink further aligning 76 additional artists, thus enhancing the alignment process beyond WES’ capabilities.
KW - ArtGraph
KW - Entity alignment
KW - Knowledge-graphs
KW - Large Language Models
KW - Wikidata
UR - http://www.scopus.com/inward/record.url?scp=85178311919&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85178311919
VL - 3540
T3 - CEUR Workshop Proceedings
BT - Semantic Web and Ontology Design for Cultural Heritage 2023
CY - Athens, Greece, November 7, 2023
T2 - 2023 International Workshop on Semantic Web and Ontology Design for Cultural Heritage, SWODCH 2023
Y2 - 7 November 2023
ER -