A multilingual, multimodal, and machine-learning-assisted infrastructure for historical formulaic texts
ANNOPHIS is a research infrastructure for the annotation, analysis, enrichment, and comparison of historical texts. It brings together expertise in historical languages, digital humanities, natural language processing, and information technology.
Research focus
ANNOPHIS supports research on historical formulaic texts, with Ancient Greek and Latin as core languages while remaining open to other historical languages and corpora.
The infrastructure supports:
- linguistic and textual annotation;
- metadata and text-structural analysis;
- links between texts and images through IIIF;
- machine-learning-assisted annotation and validation;
- comparative research across corpora and languages.
Platform
ANNOPHIS is being developed as a modular and interoperable research platform combining text access, annotation services, metadata, image integration, authentication, and machine-learning workflows.
The platform uses established standards such as W3C Web Annotation and IIIF to facilitate interoperability and long-term reuse.
Learn more about the platform →
Research and collaborations
ANNOPHIS builds on existing research projects and supports new doctoral, postdoctoral, and collaborative research.
Explore projects & collaborations →
Funding
ANNOPHIS is funded by the Research Foundation – Flanders (FWO) as a Medium-Scale Research Infrastructure project.
