Tools

Software & services

Tools portal

A suite for working with structured knowledge in the humanities and social sciences. Each tool has its own documentation; the links on the right open the applications themselves.

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.

Data

Datasets & ontologies

All datasets

Outputs

Publications

2024 4 items
2025 6 items including two edited volumes of the TOTh proceedings
2026 3 items
Book chapter

The Contribution of Ontologies to Language Curriculum Research: Semantic Structuring for Interoperability and Analysis

Roche, C., & Katis, E. In Artificial Intelligence in Literacy Education: Foundations, Practices and Innovations. Routledge.

Routledge
Forthcoming & in press 7 items accepted or announced; references completed on publication
Book

Une théorie du concept pour la terminologie

Roche, C. Athens: Herodotos.

Forthcoming
Conference paper

Towards a Conceptualization of an Archaic Lyrical Agora

Giannadakis, R. TOTh 2025: Terminology & Ontology. Presses Universitaires Savoie Mont Blanc. Related: ALyrA.

TOTh 2025
Edited volume

Proceedings of the TOTh 2025 Conference

Roche, C., Papadopoulou, M., Giannadakis, R., & Vachon, L. (Eds.). Presses Universitaires Savoie Mont Blanc.

Proceedings
Book chapter

Δημιουργώντας από το μηδέν ένα ψηφιακό σώμα κειμένων: η περίπτωση της Επτανησιακής Πεζογραφίας του 19ου αιώνα

Tiktopoulou, K., & Koidaki, F. [Creating a digital corpus from scratch: the case of 19th-century Ionian prose fiction]. In G. Fragkaki & N. Mathioudakis (Eds.), Ψηφιακές εφαρμογές στη νεοελληνική λογοτεχνία. Athens: Gutenberg.

Gutenberg

Code

Software repositories

GitHub organisation

The lab's software is released under the PolyForm Noncommercial 1.0.0: free to use, modify and share for any purpose that is not primarily commercial, with the licence and notices carried forward.

Data

Open-Data

Curated collection of the open datasets and ontologies, supporting digital humanities, computational philology, Greek NLP and cultural heritage data. This repository holds data rather than software, so it carries the dataset terms, not a software licence — see the dataset pages.

Data terms
Application

RDF-Graph-Viewer

Upload RDF/XML, extract metadata and statistics, visualise properties as an interactive graph, run SPARQL queries. Supports TEDI-built ontoterminologies. Documentation.

PolyForm NC
Application

Text-File-Analyser

Desktop application for text analysis: word frequency, named entity recognition, pattern extraction and automatic language detection.

PolyForm NC

Networks

Infrastructure & membership

Member since 2026

OPERAS

TALOS Lab is an ordinary member of OPERAS, the European research infrastructure for open scholarly communication in the social sciences and humanities. Announcement ↗

Europe
Repository

EU Open Research Repository

All seven datasets are deposited in the European Commission's Zenodo community, each with a registered DOI and versioned files.

Zenodo
Discovery

OpenAIRE

Every deposit is indexed in OpenAIRE, so the data is discoverable through the European open science graph as well as through this site.

Indexed
Funder

Horizon Europe ERA Chairs

TALOS AI4SSH, grant agreement 101087269. Project record on CORDIS, DOI 10.3030/101087269.

2023–2028
Collaborations

Partner network

Nineteen partner organisations: standards bodies, research groups, sister projects and universities across Europe, China and the Gulf.

19 partners
Institution

University of Crete

TALOS Lab was founded by publication in the Official Greek Government Gazette (FEK 4617B/07-08-2024), which also approved its operational regulation.

ROR 00dr28g20

Policy

Open access & licensing

Publications

Work produced by the laboratory is published open access wherever the venue allows it.

Data

Datasets are deposited in the European Commission's EU Open Research Repository on Zenodo, each with a registered DOI and versioned files, so that a citation resolves to a fixed version rather than to a moving target. They are built to be FAIR: findable through the DOI and OpenAIRE, accessible over an open SPARQL endpoint, interoperable through RDF and shared vocabularies, and reusable through documented terms and definitions.

Datasets are currently released under CC BY-NC-ND 4.0.

Software

The tools are released under the PolyForm Noncommercial 1.0.0: free to use, modify and share for any purpose that is not primarily commercial, with the licence and notices carried forward. It is source-available rather than open source, since the noncommercial restriction falls outside the Open Source Definition.

The code is published in the TALOS-AI4SSH GitHub organisation.

The TEDI ontoTerminology Editor is the exception. It is distributed by the University of Crete free of charge, but under a personal academic licence rather than an open source one: non-commercial, non-transferable, and not redistributable. Citing it is a condition of use.

Citing this work

Cite the DOI rather than a page on this site. Each dataset page links to its Zenodo record, where the formal citation and every version are held.