Papers: AI Part 1

Anthologies of art song have often posed challenges to discovery as contents notes are not always adequately transcribed, making it difficult for users to know what songs are contained in each score. Transcribing contents notes can be difficult, especially when the songs are in multiple languages. Through a practical and real-world example, this paper demonstrates the application of automation and artificial intelligence to enhance cataloguing records with improved contents notes and evaluates the results through a user-centred lens. We highlight possibilities for this evolving technology as well as the challenges that it can pose and explore the concept of a cost-benefit analysis of metadata work with the element of artificial intelligence being considered in a holistic manner.

This paper reports the results of a pilot project making use of data exported from WorldCat to evaluate the use of computational tools and AI in both analyzing and enhancing bibliographic (MARC) records and utilizing bibliographic information to develop a public database and data set to track the printing history of Plato's works.

Artificial Intelligence (AI) is advancing rapidly, introducing both opportunities and risks. A critical gap exists in the explicit use of Knowledge Representation (KR) within AI standards and practice. This paper presents an initial, alphabetically sorted vocabulary of terms for KRL *Knowledge Representation Learning), justifies the approach, evaluates outcomes, and sets the stage for future refinement in the context of vocabulary standardization for AIt. The work aims to bridge semantic gaps, enhance explainability, and support trustworthy AI by standardizing the terminology to be used of AI resource description. This work is presented to the metadata and vocabulary research community to foster discussions and collaboration

The current state of cultural heritage data is characterized by fragmented resources and weak interconnectivity. Efficient integration, systematic organization, and in-depth interpretation of massive, multi-source, and heterogeneous data have become the core challenges in the digital protection and inheritance of cultural heritages. The "theme - juxtaposition" structure emphasized by spatial narrative theory is highly compatible with the discrete distribution characteristics of cultural heritage elements along the Beijing Central Axis. Based on this theoretical framework, this study constructs a Beijing Central Axis ontology model that integrates metadata space, Geo narrative space, historical narrative space, and cultural narrative space. In the knowledge graph construction phase, the category system and relationship design of the ontology model are used as few-shot prompts. The Qwen3 series of large language models are employed to systematically mine the metadata information and historical event associations of the Central Axis through four stages: data extraction, relationship definition, similarity relationship calculation, and relationship normalization. The experimental results show that in the information extraction task, the overall average precision and F1 score reached 0.75 and 0.52, respectively. However, when dealing with complex relationships of cultural heritages, especially in the extraction of directions and events, the average recall rate was relatively low at only 0.41, indicating that there is still room for optimization in the model performance.