Jacco van Ossenbruggen

Handwritten archival tables contain rich historical information, yet transforming them into structured representations, such as Knowledge Graphs (KGs), requires integrating table structure recognition, handwriting recognition, and semantic interpretation—a complex multimodal process. End-to-end AI implementations can obscure these steps, resulting in opaque algorithmic operations that hinder human oversight, critical assessment, and trust. To address this, we present a modular, provenance-aware pipeline to convert handwritten tabular images into KGs supporting human–AI collaboration. The pipeline decomposes the workflow into three stages—table reconstruction, information extraction, and KG construction—while exposing intermediate representations for inspection, evaluation, and correction. A key contribution of our approach is the systematic integration of data provenance at every stage, ensuring that all extracted entities and literals remain traceable to their visual and textual origins. The proposed pipeline is demonstrated through a number of experiments on real-world archival material concerning military careers. The results across three different table reconstruction variants highlight the importance of modularisation. By coupling modularity with data provenance, our work advances transparent and collaboratively controllable image-to-KG pipelines for complex historical data.

Temporal data are crucial in many research activities within Digital Humanities (DH) and Cultural Heritage (CH). At the same time, there is a growing need for visualization tools to explore events in Linked Data (LD). This article investigates LD visualization tools that address event data in association with temporal data for research purposes in DH and CH. We analyze the availability of Wikidata visualization tools capable of handling event data for DH and CH research and propose ways to improve visualization tools to better represent temporal data in Wikidata. We identified 14 requirements based on principles from the information visualization domain, as well as an analysis of previous studies and existing tools. We design and develop a Wikidata-centric tool to meet these requirements. This tool is then evaluated through focus groups and questionnaires with DH and CH experts. The results of the evaluation show overall positive feedback and highlight the implicit need and value of visualization tools that handle events in Wikidata for research in DH and CH. In addition, they indicate the improved accessibility and visualization capabilities of Wikidata through the seven time-related functionalities of the tool.

Question answering over Scholarly Knowledge Graphs (SKGs) remains a challenging task due to the complexity of scholarly content and the intricate structure of these graphs. Large Language Model (LLM) approaches could be used to translate natural language questions (NLQs) into SPARQL queries; however, these LLM-based approaches struggle with SPARQL query generation due to limited exposure to SKG-specific content and the underlying schema. We identified two main types of errors in the LLM-generated SPARQL queries: (i) structural inconsistencies, such as missing or redundant triples in the queries, and (ii) semantic inaccuracies, where incorrect entities or properties are shown in the queries despite a correct query structure. To address these issues, we propose FIRESPARQL, a modular framework that supports fine-tuned LLMs as a core component, with optional context provided via retrieval-augmented generation (RAG) and a SPARQL query correction layer. We evaluate the framework on the SciQA Benchmark using various configurations (zero-shot, zero-shot with RAG, one-shot, fine-tuning, and fine-tuning with RAG) and compare the performance with baseline and state-of-the-art approaches. We measure query accuracy using BLEU and ROUGE metrics, and query result accuracy using relaxed exact match(RelaxedEM), with respect to the gold standards containing the NLQs, SPARQL queries, and the results of the queries. Experimental results demonstrate that fine-tuning achieves the highest overall performance, reaching 0.90 ROUGE-L for query accuracy and 0.85 RelaxedEM for result accuracy on the test set.

Statements on the propagation of bias by recommender systems are often hard to verify or falsify. Research on bias tends to draw from a small pool of publicly available datasets and is therefore bound by their specific properties. Additionally, implementation choices are often not explicitly described or motivated in research, while they may have an effect on bias propagation. In this paper, we explore the challenges of measuring and reporting popularity bias. We showcase the impact of data properties and algorithm configurations on popularity bias by combining real and synthetic data with well known recommender systems frameworks. First, we identify data characteristics that might impact popularity bias, and explore their presence in a set of available online datasets. Accordingly, we generate various datasets that combine these characteristics. Second, we locate algorithm configurations that vary across implementations in literature. We evaluate popularity bias for a number of datasets, three real and five synthetic, and configurations, and offer insights on their joint effect. We find that, depending on the data characteristics, various configurations of the algorithms examined can lead to different conclusions regarding the propagation of popularity bias. These results motivate the need for explicitly addressing algorithmic configuration and data properties when reporting and interpreting bias in recommender systems.

Traditional dataset retrieval systems rely on metadata for indexing, rather than on the underlying data values. However, high-quality metadata creation and enrichment often require manual annotations, which is a labour-intensive and challenging process to automate. In this study, we propose a method to support metadata enrichment using topic annotations generated by three Large Language Models (LLMs): ChatGPT-3.5, GoogleBard, and GoogleGemini. Our analysis focuses on classifying column headers based on domain-specific topics from the Consortium of European Social Science Data Archives (CESSDA), a Linked Data controlled vocabulary. Our approach operates in a zero-shot setting, integrating the controlled topic vocabulary directly within the input prompt. This integration serves as a Large Context Windows approach, with the aim of improving the results of the topic classification task. We evaluated the performance of the LLMs in terms of internal consistency, inter-machine alignment, and agreement with human classification. Additionally, we investigate the impact of contextual information (i.e., dataset description) on the classification outcomes. Our findings suggest that ChatGPT and GoogleGemini outperform GoogleBard in terms of internal consistency as well as LLM-human-agreement. Interestingly, we found that contextual information had no significant impact on LLM performance. This work proposes a novel approach that leverages LLMs for topic classification of column headers using a controlled vocabulary, presenting a practical application of LLMs and Large Context Windows within the Semantic Web domain. This approach has the potential to facilitate automated metadata enrichment, thereby enhancing dataset retrieval and the Findability, Accessibility, Interoperability, and Reusability (FAIR) of research data on the Web.