The NONWESTLIT project has made substantial progress from its inception, focusing primarily on the development of two critical databases: the NONWESTLIT Literary Periodicals Database (DB1) and the NONWESTLIT Translations Database (DB2). These databases target the literary and cultural discourse of non-Western imperial traditions, the Ottoman, Russian, and Japanese empires. The main work packages involved include Data Acquisition, Qualitative and Quantitative Analysis, Correlations and Theory, and Translation and Open Access Digitization.
DB1, established during the first half of the project, has been instrumental in creating a comprehensive, multi-level, multi-label text classification dataset from 19th-century periodicals across the three studied cultures. This includes collecting, categorizing, and annotating a vast array of documents, leading to a unique multilingual text classification dataset, which is unprecedented in literary studies. DB2 focuses on the translations of European literary works into Ottoman, Russian, and Japanese, offering insights into the cross-cultural literary exchanges of the period. It correlates original works with their translations, providing a deeper understanding of the publication dynamics and literary influences across these cultures.
Significant technological advancements have been made, particularly in the use of large language models for analyzing this rich dataset, establishing NONWESTLIT as a pioneering effort in applying AI to the study of historical and low-resource languages.
Throughout this period, the project has successfully conducted numerous workshops, published peer-reviewed articles, and engaged in a wide range of dissemination activities, all of which surpass the initial milestones and deliverables outlined in the project's action plan. This robust engagement has not only advanced the project's objectives but has also fostered significant interdisciplinary collaboration and intellectual exchange among its members.