Abstract
Knowledge Graphs (KGs) are emerging as powerful tools for cultural heritage
(CH) applications, offering a structured and interconnected way to represent
vast and diverse information about artifacts, historical events, creators,
and more. As KGs transform disparate, siloed, CH artifacts into a rich,
navigable web of entities and relationships, allow at the same time for more
intelligent search, discovery, and analysis, moving beyond keyword matching to understanding the
underlying meaning and connections within CH collections. KGs facilitate the integration of
heterogeneous sources of cultural data, from museum inventories and archival documents to
archaeological findings and expert annotations, creating a unified knowledge base that can
support various user groups, including researchers, curators, and the general public.
Despite previous and ongoing research work in the use of KGs in CH there are still significant
research challenges, as CH research encompasses a multitude of disciplines from the humanities
and social sciences (e.g. archaeology, cultural anthropology, history and art history),
to natural sciences (e.g. biology, chemistry, physics) and exact sciences (e.g. mathematics,
computer and data sciences), each with their own distinct methodologies and workflows.
The first important one stems from the heterogeneity and fragmentation of data.
CH data is notoriously diverse in format, quality, and granularity, ranging from structured
databases to unstructured texts and multimedia. Integrating this disparate information into a
coherent graph requires robust methodologies for data harmonization, entity resolution, and
schema alignment. Another challenge is the inherent ambiguity and subjectivity within CH knowledge.
Historical interpretations can vary, and provenance information is often incomplete or uncertain.
KGs need to be able to represent and manage this uncertainty, perhaps through probabilistic
links or by incorporating multiple perspectives. Furthermore, scalability and maintainability
are crucial concerns. And as usual user interaction and visualization remain active research areas.
Especially, the ability to add query-to-text interfaces through various AI LLMs emerges as an
important aspect for the uptake of the use of KGs in CH applications.
But integrating AI with KGs introduces further complexities.
A key concern is bias amplification: as AI models get trained on historical data,
they can perpetuate societal biases, leading to skewed interpretations.
This requires careful data curation and explainable AI (XAI) solutions so as to ensure fairness.
The interpretability of AI-driven insights is another challenge; "black box" AI systems
hinder understanding of their rationale, clashing with CH's emphasis on provenance and human
validation. Interesting questions arise on how we can use KGs to tackle these issues of bias
and transparency in the CH domain. Extending these questions to tackle issues of AI generated
CH content or authenticity of CH artifacts, could provide additional roles for the use of
cultural KGs.
The workshop aims at exploring problems and solutions in this area and leverage existing
efforts in the European and international level like the projects ECHOES (EU) and RICHES (UK)
and explore how emerging CH infrastructures can benefit from the advanced use of KGs.
Topics of interest
Organizers
Call for Papers
The workshop invites scholars and R&D experts in related fields to submit papers with unpublished results.
Authors must prepare their papers following Springer's Instructions for Authors of Proceedings.
The maximum length for submissions is 15 pages.
Papers will be submitted in PDF format using EasyChair: https://easychair.org/conferences/?conf=ijckg2025
(make sure to select the track with name "Workshop "Knowledge Graphs in Cultural Heritage")
Important Dates
Scope and Objectives
Quantum computing is poised to revolutionize the way we process, store, and retrieve information.
As this technology matures, its implications for data and knowledge management become increasingly significant.
From quantum-enhanced algorithms for database search and optimization, to novel paradigms in distributed data
storage and quantum knowledge representation, the intersection of quantum computing and data/knowledge management
opens a rich field of exploration.
This workshop invites original contributions that advance the theoretical, practical, and experimental
understanding of how quantum computing impacts data and knowledge management.
Topics of interest (include but are not limited to):
Important Dates
Submission Guidelines:
All submissions must be original and not under review elsewhere.
Authors must prepare their papers following Springer's Instructions for Authors of Proceedings.
The maximum length for submissions is 15 pages.
Organizers
PC Members
Supported:
This work was supported by DEDALUS - Data Management using Quantum Computing project (TA 5180519)
funded by SUB1.1 Clusters of Research Excellence (CREs), Greece. https://dedalus.csd.uoc.gr/.
Contact & Inquiries:
For questions or further information, please contact the organizers at tzitzik 'AT' ics.forth.gr & kondylak 'AT' ics.forth.gr