General information
The iConTxt project brings a transformative innovation to the DLBT by integrating advanced artificial intelligence to unlock the full potential of its unique multilingual collections. As one of the most comprehensive and authoritative resources on Dutch literature in translation, the DLBT holds vast scholarly value, yet much of this material remains underused due to language and accessibility barriers. iConTxt directly addresses this challenge.
Developed collaboratively by eight European universities (see: Cooperations, partners and projects) and in partnership with the Vienna University Library and the Vienna University Computer Centre, the project leverages Large Language Models (LLMs) to automate metadata curation, generate English-language summaries and analytical information from reception materials and, where legally permissible, English-language versions of source materials, and produce new contextual knowledge derived from existing database materials. In this way, iConTxt transforms isolated records into interconnected, research-ready information.
By embedding these AI capabilities directly into the YARM[1] software that powers the DLBT, iConTxt transforms the library into a dynamic, self-enriching research infrastructure. It enables user-friendly access for researchers, students, translators, literary agents, cultural institutions, and policymakers, fostering new opportunities for cross-cultural analysis, educational innovation, and literary exchange. Its open-source design ensures that the resulting tools and methodologies remain freely available to registered users. It enhances global accessibility to cultural heritage, strengthens the visibility of Dutch literature worldwide, and contributes to a broader understanding of literature as a living, transnational ecosystem.
Research infrastructure
and use of source materials
iConTxt supports scientific research into the reception of literary works and their translations. Its research infrastructure comprises iConTxt and iConTxt-Info. iConTxt-Info serves as the project's research and knowledge environment, in which bibliographical information, reception documents and other research materials are collected, structured, processed and analysed. These materials include content from publicly available sources as well as digitised reception documents originating from the Digital Library and Bibliography of Literature in Translation (DLBT), including archival material collected since the late 1980s.
AI-assisted analysis of literary reception
Reviews and other reception documents to which the university has lawful access may be subjected to automated text and data analysis using artificial intelligence, including Large Language Models (LLMs) accessed through the OpenAI API. The purpose of this analysis is to generate new scholarly information from the source materials. This may include identifying and synthesising critical assessments, recurring themes and issues, agreements and disagreements between reviewers, as well as patterns and trends in the reception of literary works and their translations.
The resulting reception overviews primarily consist of independently generated summaries, paraphrases and analytical classifications, accompanied by references to the underlying sources. By identifying and structuring significant themes and issues addressed in individual reception documents, iConTxt facilitates comparative research across literary works, translations, languages, periods and reception contexts.
Source materials used for this analysis remain under the control of the university and may be retained within the research infrastructure where required for scientific research, including further analysis and the verification of research results. Appropriate technical and organisational measures are applied to their processing, storage and access. API data sharing for model improvement is disabled.
Source materials and publicly available research information
iConTxt maintains a distinction between source materials held and processed within the research infrastructure and information made publicly available through iConTxt.
The inclusion of a copyright-protected document in the research corpus does not in itself result in that document being made publicly accessible. Publicly presented research results primarily consist of bibliographical information, independently generated summaries and paraphrases, analytical classifications, contextual information and other information derived from scholarly analysis.
Where the original wording of a copyright-protected reception document is reproduced, direct quotations are limited to the extent justified by the scholarly purpose and are accompanied by appropriate source references. Complete translations of reception documents are made publicly available only where the underlying source documents are no longer protected by copyright or where another appropriate legal basis permits their publication.
Book covers as sources for research
The DLBT also documents book covers of translated editions as visual paratexts associated with the bibliographical records of particular translations and editions. In addition to assisting with the identification and documentation of editions, book covers constitute potential source material for research into the publication and reception history of translated literature.
Cover design, imagery, typography and changes across editions, publishers, periods and target languages can be studied comparatively to investigate how translated works have been framed, marketed and presented to different readerships and cultural contexts. Cover images are therefore incorporated into the project's research environment of iConTxt as potential sources for the study of translation and reception history.
[1] YARM – Reference management system developed at the Vienna University Library. YARM provides the database and the tools of the DLBT and links the DLBT with PHAIDRA.
