AthDGC · Athens-PROIEL

An open diachronic Greek treebank with Indo-European parallels

Nikolaos Lavidas

National and Kapodistrian University of Athens (NKUA)

June 20, 2026

Athens Digital Glossa Chronos

The Athens Digital Glossa Chronos (Athens-PROIEL (the dependency-treebank (a collection of sentences whose grammatical structure has been analysed and stored) standard for early Indo-European languages, developed at Oslo)) is an open PROIEL-style dependency treebank spanning Greek diachrony with Indo-European parallels.

NKUA · Division of Language-Linguistics, Department of English Language and Literature, School of Philosophy

Funded by HFRI (Project No. 20577) · Greece 2.0 NRRP

Corpus + Tools

AthDGC is both a continuously-updated PROIEL XML 2.0 (the file format that stores each sentence as a tree of word-by-word grammatical relations, developed at Oslo) treebank and an open-source computational diachronic-linguistics toolkit:

  • LightSIDE (an open-source text-mining workbench developed at Carnegie Mellon)-compatible feature extraction + classifier training
  • NoSketch-style concordancer (a search tool that shows every occurrence of a word in its surrounding context)
  • Fine-tuned (further trained on new data to adapt it to a particular text type) Stanza (Stanford’s open-source Python workflow that automatically tags, lemmatises, and parses sentences) checkpoints (Byzantine, Late-Byzantine, Modern adaptations)
  • Argument-structure extractor
  • Cross-lingual alignment (matching corresponding words or sentences between texts in different languages) viewer (Neo4j (a graph database that stores data as nodes and connections rather than as tables))
  • Quarto (an open-source publishing system that builds websites, slides, papers, and posters from a single source) template pack for any DH project (this very deck is built with it)

The corpus

Covers:

  • Homeric and Archaic Greek (Homer, Hesiod, Sappho, Pindar)
  • Classical (Aeschylus, Sophocles, Euripides, Aristophanes, Plato, Aristotle)
  • Koine and NT (Plutarch, Strabo, Lucian, the New Testament)
  • Late Antique (Eusebius, Basil, Chrysostom, Procopius)
  • Byzantine (Psellos, Anna Komnene, John of Damascus, Niketas Choniates)

with NT verse-level cross-alignment to Latin (Vulgate), Gothic (Wulfila), and Old Church Slavonic (Marianus).

Current state (v0.4)

Metric Value
Greek periods covered 8 (Archaic - Modern)
IE cross-aligned witnesses 4 (Latin Vulgate, Gothic Wulfila, OCS Marianus, Classical Armenian in ingestion)
Per-witness verse counts v0.5 release notes (post-ARIS audit)

Workflow

  1. Discovery, daily harvest from archive.org, Perseus, First1K, Wikisource, Diorisis
  2. Filtering, Greek-script ratio, apparatus-criticus rejection, dedup
  3. Conversion, PROIEL XML 2.0
  4. Annotation, Stanza grc_proiel + analogous models per parallel language
  5. Argument-structure, subject, object, oblique, voice, aspect per verb
  6. Cross-alignment, LaBSE (a multilingual sentence-embedding model that maps sentences from many languages into a common vector space) + AwesomeAlign (a word-alignment procedure that uses multilingual-BERT attention to match words across translations) (mBERT)
  7. Storage, PROIEL XML + JSONL (a plain-text data format that stores one record per line) + Qdrant + Neo4j

Scholarly focus

  • Retranslation of influential texts (Iliad, NT, Septuagint Psalms, classical historiography)
  • Retelling chains across periods and languages
  • Argument structure (the set of obligatory and optional partners a verb requires, e.g. subject, object, oblique) under retranslation

Team

  • Lavidas (PI) · Nikiforidou · Haug (Oslo) · Kulikov (Ghent)
  • Geka · Symeonidis · Michalareas
  • Chionidi · Tsiropina · Plakoutsi · Argyropoulos

NKUA · Athens Digital Glossa Chronos Research Network

How to cite

Lavidas, N., Nikiforidou, K., Haug, D., Kulikov, L., Geka, V., Symeonidis, V., Michalareas, T., Chionidi, S., Tsiropina, A., Plakoutsi, E., and Argyropoulos, E. (2026). AthDGC: Athens Digital Glossa Chronos. Zenodo (an open research-data repository hosted at CERN that mints permanent DOIs).

DOI (Digital Object Identifier, a permanent web link for a published artefact): 10.5281/zenodo.20439182

Thank you

Funded by the Hellenic Foundation for Research and Innovation (HFRI) under the 3rd Call for HFRI Research Projects to support Post-Doctoral Researchers, Project No. 20577; with complementary support from the Greece 2.0 National Recovery and Resilience Plan.

Compute supplied by GRNET ARIS (the Greek national high-performance computing cluster, run by GRNET) (Greek national HPC (high-performance computing, i.e. a cluster of fast machines used for heavy computation)), allocation pa260305.