MBMichael Bryant

Michael Bryant

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Michael Bryant has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

    • 3 July 2025
    • Published by HAL in HAL
    Open Access

    Multilingual Automated Subject Indexing: a comparative study of LLMs vs alternative approaches in the context of the EHRI project

    by Maria Dermentzi, Mike Bryant, Fabio Rovigo, Herminio García-González

    The European Holocaust Research Infrastructure (EHRI) facilitates transnational Holocaust research by making information about dispersed archival sources accessible through the EHRI Portal. An important aspect of effectively integrating this information is the indexing of collection metadata from institutions worldwide based on a common domain-specific controlled vocabulary (EHRI Terms). However, challenges persist in harmonising the use of subject headings across institutions. Hence, this paper explores approaches for Automated Subject Indexing (ASI), including statistical, lexical, and fusion approaches, as well as the use of Large Language Models (LLMs) for zero-shot classification. We describe how we use archival descriptions ingested into the EHRI Portal as training data for Machine Learning (ML) algorithms, including for fine-tuning an LLM. We evaluate LLM- and non-LLM-based tools quantitatively and qualitatively, with our focus being to explore if and to what extent LLMs can play a role in developing reliable ASI tools. We conclude that although some tools under evaluation score quite highly, they are at present best suited for use as part of semi-ASI workflows with human oversight. However, this study charts a promising course towards developing tools that are reliable enough to facilitate subject indexing processes and enhance metadata according to the FAIR Data Principles.

  • Open Access

    The Holocaust Archival Material Knowledge Graph

    by Herminio García-González, Mike Bryant

    Research into the Holocaust faces particular challenges due to the diversity and dispersal of its sources. The EHRI Portal, one of the main outputs of the EHRI project, is a platform for contextualising and integrating metadata about Holocaust-related archival material. In this work we undertake to deliver the EHRI Portal’s archival metadata as Linked Open Data in order to explore the benefits that this model can provide to the field in terms of decentralised data access and integration with the wider Semantic Web. We describe the process of transforming the existing data to a Knowledge Grah aligned with the new ICA conceptual model, Records in Contexts (RiC). As part of this process we describe the challenges and limitations of this alignment, along with future developments that could result in a better fit with our use-case. We envision this work as the first step in delivering Holocaust data to the Semantic Web, allowing partner institutions to evaluate its capabilities and potentially adopt it for their own solutions, making the field more interconnected.


  • Open Access

    The CENDARI Infrastructure

    by Nadia Boukhelifa, Mike Bryant, Nataša Bulatović, Ivan Čukić, Jean-Daniel Fekete, Milica Knežević, Jörg Lehmann, David Stuart, Carsten Thiel

    The CENDARI infrastructure is a research-supporting platform designed to provide tools for transnational historical research, focusing on two topics: medieval culture and World War I. It exposes to the end users modern Web-based tools relying on a sophisticated infrastructure to collect, enrich, annotate, and search through large document corpora. Supporting researchers in their daily work is a novel concern for infrastructures. We describe how we gathered requirements through multiple methods to understand historians’ needs and derive an abstract workflow to support them. We then outline the tools that we have built, tying their technical descriptions to the user requirements. The main tools are the note-taking environment and its faceted search capabilities; the data integration platform including the Data API, supporting semantic enrichment through entity recognition; and the environment supporting the software development processes throughout the project to keep both technical partners and researchers in the loop. The outcomes are technical together with new resources developed and gathered, and the research workflow that has been described and documented.


  • Open Access

    The European Holocaust Research Infrastructure Portal

    by Tobias Blanke, Michael Bryant, Michal Frankl, Conny Kristel, Reto Speck, Veerle Vanden Daelen, René Van Horik

    Over the course of the past century, there have been significant changes in the practices of archives driven by the massive increase in the volume of records for archiving, a larger and more diverse user base, and the digital turn. This paper analyses work undertaken by the European Holocaust Research Infrastructure project (EHRI) to develop heritage archives into research infrastructures by connecting their knowledge and making it relevant for research. In the article, we focus on EHRI’s work on an integrated collection portal, acting as a central gateway to the rich information on Holocaust-related sources. At the time of writing, the portal contains over 150,000 descriptions of over 1,850 institutions that hold Holocaust-related archival material in 51 countries. In addition, it hosts concise reports that provide in-depth per-country information about the Holocaust history and archival situation in 47 countries, topic-focused research guides, and a range of other services. The article presents how the EHRI portal work connects to the state of the art of heritage portals and the novel solutions we had to develop to align the portal with the requirements of a research infrastructure.


  • Developing the collection graph

    by Tobias Blanke, Michael Bryant, Reto Speck

    Purpose: – In 2010 the European Holocaust Research Infrastructure (EHRI) was funded to support research into the Holocaust. The project follows on from significant efforts in the past to develop and record the collections of the Holocaust in several national initiatives. The purpose of this paper is to introduce the efforts by EHRI to create a flexible research environment using graph databases. The authors concentrate on the added features and design decisions to enable efficient processing of collection information as a graph. Design/methodology/approach: – The paper concentrates on the specific customisations EHRI had to develop, as the graph database approach is new, and the authors could not rely on existing solutions. The authors describe the serialisations of collections in the graph to provide for efficient processing. Because the EHRI infrastructure is highly distributed, the authors also had to invest a lot of effort into reliable distributed access control mechanisms. Finally, the authors analyse the user-facing work on a portal and a virtual research environment (VRE) in order to discover, share and analyse Holocaust material. Findings: – Using the novel graph database approach, the authors first present how we can model collection information as graphs and why this is effective. Second, we show how we make collection information persistent and describe the complex access management system we have developed. Third, we outline how we integrate user interaction with the data through a VRE. Originality/value: – Scholars require specialised access to information. The authors present the results of the work to develop integrated research with collections on the Holocaust researchers and the proposals for a socio-technical ecosystem based on graph database technologies. The use of graph databases is new and the authors needed to work on several innovative customisations to make them work in the domain.


  • The EHRI Project - Virtual Collections Revisited

    by Mike Bryant, Linda Reijnhoudt, Reto Speck, Thibault Clerice, Tobias Blanke


  • Back to our data — Experiments with NoSQL technologies in the Humanities

    by Tobias Blanke, Michael Bryant, Mark Hedges

    In this short paper we discuss our work on developing a data infrastructure for Holocaust research. Faced with the challenge of integrating data with widely varying characteristics, we decided to pursue an approach based on the property graph model and corresponding graph databases. These provide intuitive modelling capabilities and the ability to fluently evolve in structure to meet the needs of the data but require more basic implementation work, as the technology is less mature.


  • Open source optical character recognition for historical research

    by Tobias Blanke, Michael Bryant, Mark Hedges

    Purpose: This paper aims to present an evaluation of open source OCR for supporting research on material in small‐ to medium‐scale historical archives.Design/methodology/approach: The approach was to develop a workflow engine to support the easy customisation of the OCR process towards the historical materials using open source technologies. Commercial OCR often fails to deliver sufficient results here, as their processing is optimised towards large‐scale commercially relevant collections. The approach presented here allows users to combine the most effective parts of different OCR tools.Findings: The authors demonstrate their application and its flexibility and present two case studies, which demonstrate how OCR can be embedded into wider digitally enabled historical research. The first case study produces high‐quality research‐oriented digitisation outputs, utilizing services that the authors developed to allow for the direct linkage of digitisation image and OCR output. The second case study demonstrates what becomes possible if OCR can be customised directly within a larger research infrastructure for history. In such a scenario, further semantics can be added easily to the workflow, enhancing the research browse experience significantly.Originality/value: There has been little work on the use of open source OCR technologies for historical research. This paper demonstrates that the authors' workflow approach allows users to combine commercial engines' ability to read a wider range of character sets with the flexibility of open source tools in terms of customisable pre‐processing and layout analysis. All this can be done without the need to develop dedicated code.


  • Linked data for humanities research — The SPQR experiment

    by Tobias Blanke, Gabriel Bodard, Michael Bryant, Stuart Dunn, Mark Hedges, Michael Jackson, David Scott

    Ancient texts represent a primary source for research in the classics. A substantial body of digital material has evolved enriching these texts. Unfortunately these data are often distributed across myriad locations, stored in diverse and incompatible formats and are either not available online or are made available only in isolation. This paper describes an investigation into using linked data principles and technologies to build bridges between these islands of data to deliver an integrated data landscape through which researchers can explore and so seek to understand this data. The evaluation revealed that researchers were of the opinion that the linked data representation, and its visualisation as graphs, offers an intuitive and usable means of exploring and understanding the data, exceeding the capabilities offered by current online portals to classics data.


  • Ocropodium: open source OCR for small-scale historical archives

    by Tobias Blanke, Michael Bryant, Mark Hedges

    Large-scale digitization projects dealing with text-based historical material face challenges that are not well catered for by commercial software. This article discusses the results of a project to build a scalable OCR workflow for historical collections based on open source tools that is particularly tailored towards use in small-scale historical archives. It argues that open source tools allow for better customization to match these requirements, particularly with regard to character model training and per-project language modelling. We offer insights into our accuracy evaluation results of various open source OCR tools, as well as a case study about the challenges and opportunities of open source OCR in historical archives.