Web application

Text Analyzer

Analyses Greek corpora: frequency, collocations and co-occurrence networks, plus LLM-backed entity recognition, tagging, sentiment and topic modelling for Ancient and Modern Greek.

Working with the suite

How the tools fit together

Datasets

The tools are separate applications, but they are built around one artefact: an ontoterminology expressed in RDF. Most work in the laboratory moves through them in roughly the same order.

1. AuthorTedi: build the concept system and the term lists, then export RDF/OWL
2. InspectOTV for the hierarchy, RDF Graph Viewer (web) or (desktop) version for the network
3. ExtendKnowledge Graph Editor: add or edit entities and relations by hand
4. PopulateText Analyzer: find entities and terms in a corpus to feed back into the model
5. QuerySPARQL Endpoint: ask questions of the published graph

The data behind the tools

The endpoint, the ontology viewer and the graph viewers all read the same published datasets. Each has a page of its own describing what it models, its graph IRI, and how to cite it.

Licensing

The tools do not share a licence. Check the page for whichever you intend to use, and note that a licence covering a tool does not cover the data it operates on — the datasets carry their own terms.

TediPersonal academic licence: free for teaching and research, non-commercial, not redistributable
All other toolsPolyForm Noncommercial 1.0.0

Citing the tools

There is no single citation for the suite. Cite the individual tool you used. Each documentation page carries its preferred form and acknowledge the funder:

This work used tools developed by the TALOS AI4SSH Laboratory,
University of Crete, funded by the European Union's Horizon Europe
programme under grant agreement No 101087269.

Support

Bugs and feature requests for the tools with public repositories are best raised as issues on GitHub. For anything else, or if you are unsure which tool your question concerns, write to talosailab@gmail.com.