Connecting Climate Discourse and Religious Language (from 2024)
Funding provided by the Vrije Universiteit Amsterdam Profile Theme Connected World.
Willem van Peursen Yusuf Çelik, Jan Jorrit Hasselaar (FRT), Sandjai Bhulai (BETA), Meike Morren (SBE)
This project combines Natural Language Processing, text-mining, religious studies and social sciences to address question such as: how is climate conversation shaped by religious concepts and what does this reveal about the interrelatedness of world view and attitudes towards nature and climate? The project involved the mining of websites of important environmental NGOs such as Greenpeace.
Seeing The Words: Evaluating AI-generated Biblical Art (from 2023)
Hidde Makimei, Shuai Wang, Willem Th. Van Peursen
This project involves the generation of a large dataset of over 7K images using biblical text as prompts and the evaluation of these images with multiple neural network-based tools on various aspects. The prompts are the biblical passages on the expulsion from Paradise, the Tower of Babel, the binding of Isaac, Moses Found and the Last Supper. The generated images are further compared with Renaissance and Baroque paintings based on the same episodes. In this way it explores the complex interaction between text, imagination, conventional representations and AI the performance of the AI generators.
Ge’ez project morphological encoding (from 2024)
Garry Jost, Jorik Groen, Constantijn Sikkel, Yusuf Çelik, Martijn Naaijer, Willem van Peursen
This project explores the potential to apply the model of morphological analysis developed at the ETCBC to Classical Ethiopic (Ge’ez). This entails the definition of transliteration conventions and the set up of rules for the encoding of morphemes and the functional deductions based on the morphological analysis. The aim is that in a later stage this can be used to accelerate the morphological analysis of Ge’ez biblical texts that are now presented at https://ethiopic-tool.firebaseapp.com.
Morphological Analysis of the Syrohexaplaric Psalter (from 2023)
Funding provided by the Göttingen Septuagint Project
Logan Copley, Piotr Jutkiewicz, Willem van Peursen, Constantijn Sikkel, Yusuf Çelik
Building upon the models developed in the project “Morphological Parser for Inflectional Languages Using Deep Learning”, this project aims at the morphological encoding of the Syrohexaplaric version of the Psalms. It is a project component of the Editio critica maior of the Greek Psalter.
Qoroyo (from 2023)
Yusuf Çelik
Qoroyo is a linguistic and hermeneutical tool that facilitates multilingual presentation and annotation of textual data and the application of computational analytical methods.
Live-mapping Religious Difference Online (2023)
Funding provided by the Network Institute
Yusuf Çelik and Willem van Peursen
This project investigates the feasibility of live-mapping the differential use of religious texts in social media to identify religious issues present across digitally mediated culture. It involves two hackatons, “Text-mining social media in the age of restrictions” and “Analyzing religious language in social media” and a concluding seminar by Dr Peter M. Phillips (Centre for Digital Theology, Spurgeons College, London)
Educating Moral Leadership Grounded in Theology (from 2022)
Joint project with the School of Business and Economics (Vrije Universiteit)
Srećko Koralija, Elco van Burg (SBE), Omar Solinger (SBE), Willem van Peursen
This project combines biblical studies and theology with research inquiries in organizational studies, business, and organizational behavior. It includes questions such as: How can an exploration of religious texts enhance comprehension of moral motivation and leadership? What constitutes moral leadership, and how can a religious text, such as the Bible, aid in its definition?
Greek New Testament conversion project (from 2022)
Joint project with the Center of Biblical Languages and Computing (CBLC), Andrews University
Tony Jurg, Saulo de Oliveira Cantanhede (Andrews), Oliver Glanz (Andrews), Willem van Peursen
This project entails the conversion of Lowfat trees from the MACULA linguistic datasets for the Nestle 1904 Greek New Testament towards Text-Fabric, to facilitate computational corpus analysis.
Who Determines What the Qur’an Means: Hermeneutical Authority in Premodern and Modern Islam (2022–2023)
NIAS full year fellowship 2022/23
Pieter Coppens
In this fellowship Pieter Coppens investigated how digital tools developed by the KITAB project (Aga Khan University London) can be used to detect text reuse in the massive corpus of the tafsir tradition. He wrote a chapter for and edited volume on text reuse from the corpus of the 12th-century mystic Ibn 'Arabi in the 19th-century Qur'an commentary of Shihab al-Din al-Alusi.
Morphological Parser for Inflectional Languages Using Deep Learning (from 2021)
Funding provided by the eScience Center
Martijn Naaijer, Willem van Peursen, Constantijn Sikkel, Mathias Coeckelbergs, Yusuf Çelik, Jisk Attema (eScience Center), Dafne van Kuppevelt (eScience Center)
This project started as an eScience Center Open Small Scale Initiative (SSI) project. After the completion of the funded project (2021–2022), it continued as a research group developing tools for the morphological analysis of Hebrew, Syriac and other inflectional languages. One of its spin-offs is the Qoroyo platform.
See also this RANLP-ALP 2023 presentation and blogpost 1 and blogpost 2.
PaTraCoSy: Patterns in Translation: Using Colibri Core for the Syriac Bible (from 2021)
Funding provided by CLARIAH Fellowship programme
Mathias Coeckelbergs and Willem van Peursen
In this fellowship Mathias Coeckelbergs investigaed to what extent can linguistically uninformed features help us in tracing divergent patterns in an ancient Syriac Bible translation and its Hebrew source text, Colibri Core developed by Maarten van Gompel.
Deliverables include an LREC presentation and blogpost 1, blogpost 2 and blogpost 3.
Dhammapada latine (2021)
Bee Scherer, Yvon Mattaar, Willem van Peursen
This project concerns the creation of a Text-Fabric module with a digital version of the Dhammpada in Pali and its 19-cent. Latin translation by M. Viggo Fausbøll.
See further the GitHub page and the blogpost on the ETCBC website
Understanding Spiritual Intelligence (2020-2024)
Funding provided by the Templeton Foundation
DAST member involved: Marius Dorobantu
THis is an interdisciplinary project run by the International Society for Science & Religion, focused on understanding the nature of spiritual intelligence from psychological, computational, and theological perspectives. The project brought together renowned AI pioneers (Yorick Wilks and William Clocksin), cognitive scientists (Philip Barnard), psychologists (Fraser Watts) and theologians (Rowan Williams), and was funded by the Templeton World Charity Foundation, as part of their Diverse Intelligences initiative.
See the project website.
New Frysian Bible translation (Fryske Bibel Oersetting) (from 2017)
ETCBC members involved: Eep Talstra and Lénart de Regt
The Frysian translation of the Bible is being prepared by Stifting YKFE-FBO. Draft translations are being prepared by computer programs made by Eep Talstra based on the database.
For more information see the project website.
Database Driven E-Learning (DaDEL) (from 2018)
Joint project with the Protestant Theological University
Funding provided by the Ministry of Education, Culture and Science (OCW)
Support provided by the United Bible Societies
ETCBC members involved: Willem van Peursen and Nicolai Winther-Nielsen
This project involved the development of digital educational tools for the study of Hebrew, Aramaic and Greek, potentially be extended to other ancient languages. After the completion of the funded project (2018–2020, DaDEL was integrated in the Bible Online Learner Consortium under the umbrella of the United Bible Societies (from 2022).
CACCHT: Creating Annotated Corpora of Classical Hebrew Text (from 2018)
Funding provided by the Charis Foundation.
Martijn Naaijer, Martin Ehrensvärd, Christian Canu Højgaard, Robert Rezetko
"Creating Annotated Corpora of Classical Hebrew Texts (CACCHT) focuses on annotating and publishing textual datasets of the Hebrew Bible. Presently, we are working on a dataset of a new edition of the Samaritan Pentateuch, which can be found on GitHub (https://github.com/dt-ucph/sp)." See also the project page on GitHub and the Blogpost on the Dead Sea Scrolls Text-Fabric Module
Peshitta Portal Project (from 2017)
Funding provided by Brill Publisher and the Peshitta foundation.
Hannes Vlaardingerbroek, Constantijn Sikkel and Willem van Peursen
This project involves the creation of an electronic version of the Leiden Peshitta edition Vetus Testamentum Syriace which is available in the Brill Peshitta Online. It includes the complete critical apparatus and introductions found in the printed edition. OCR techniques were developed for the digitization of the printed edition.
For more information see this blogpost.
Semantics of Ancient Hebrew Database (long-term, ongoing)
Joint project with the Protestant Theological University
Klaas Spronk (PThU), Paul Sanders (PThU), DAST member involved: Willem van Peursen
The SAHD project aims to provide a structured and critical survey of scholarly literature on the vocabulary of classical Hebrew. The ETCBC involvement concerns the integration of textual and lexicographical data. It’s current directors are Klaas Spronk and Paul Sanders
Website: http://www.otw-site.eu/en/sahd/
Revision of the List of Peshitta manuscripts (long-term, ongoing)
Geert Jan Veldman and Willem van Peursen
This project concerns a complete revision and update of the preliminary version of the List of Peshitta manuscripts published in 1961. Project constituents include the project “Linking Syriac Liturgies and Updating and expanding the description of Peshiṭta Old Testament lectionary manuscripts made by Willem Baars”.
See further the contribution on Academia on the new format of the List, the DANS repository of the Linking Syriac Liturgies project and this [open access] and this blogpost by Geert Jan Veldman about his visit to the HMML.