AthDGC: An Open Diachronic Greek Treebank with Indo-European Parallels

2026-06-13 · Source: Computation and Language · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Research Methodology & Innovation · Depth: Expert, quick

Summary

AthDGC ("Athens-PROIEL") is an open, end-to-end workflow and dataset, representing the first openly licensed dependency-parsed treebank of Greek. It spans eight diachronic periods, from Archaic to Modern Greek, unified under a PROIEL XML 2.0 schema. This resource also features verse-level cross-alignment of the New Testament with Latin (Vulgate), Gothic (Wulfila), Old Church Slavonic (Marianus), and Classical Armenian. AthDGC leverages the PROIEL Treebank Family and employs a Stanford Stanza PROIEL-trained workflow for annotation. Sentence-level alignment is achieved using LaBSE, while word-level alignment utilizes multilingual-BERT attention through the AwesomeAlign procedure. The v0.4 release offers curated samples and an open-source toolkit, with the full annotated corpus partitions expected in the v0.5 release after audit.

Key takeaway

For NLP Engineers or Research Scientists working with historical linguistics or multilingual text alignment, AthDGC offers a critical new resource. You can utilize this open Greek treebank to train models on diachronic language evolution or to conduct comparative studies of New Testament translations. Consider integrating the PROIEL XML 2.0 schema and the provided toolkit into your research to enhance cross-linguistic analysis and model development for ancient languages.

Key insights

AthDGC provides the first openly licensed, diachronic Greek dependency treebank with multilingual New Testament alignments.

Principles

• Unify diachronic data under single schema.
• Cross-align texts for linguistic research.
• Open-source tools enhance accessibility.

Method

The workflow uses Stanford Stanza for annotation, LaBSE for sentence alignment, and multilingual-BERT attention via AwesomeAlign for word-level alignment.

In practice

• Explore diachronic Greek linguistic changes.
• Analyze New Testament translations across languages.
• Integrate PROIEL XML 2.0 schema in projects.

Topics

• Diachronic Linguistics
• Greek Language
• Dependency Treebank
• Multilingual Alignment
• PROIEL Treebank
• Natural Language Processing

Best for: AI Scientist, NLP Engineer, Research Scientist

Related on AIssential

• Koshur Diacritizer: A Byte-Level Sequence-to-Sequence Model for Kashmiri Diacritic Restoration — Koshur Diacritizer is a ByT5-small model that restores Kashmiri diacritics using a new 23.7k sentence pair dataset.
• Libras-UFPel Corpus: A Parallel Dataset of Brazilian Sign Language and Portuguese for Multimodal Research and Processing — The Libras-UFPel Corpus provides a parallel multimodal dataset for Brazilian Sign Language and Portuguese.
• A UD Parser to the Rescue: A Method for Bringing a Classical Annotated Corpus to Life Again — A knowledge-rich parsing method can effectively update classical linguistic corpora to modern annotation standards.
• IndicDB -- Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages — IndicDB reveals a significant "Indic Gap" in LLM Text-to-SQL performance for Indian languages compared to English.
• Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models — A new AG-MG parallel corpus and benchmark significantly advance Ancient Greek to Modern Greek machine translation.
• AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages — Models exhibit a significant "syntax gap" in processing African languages, struggling with their structural diversity.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Computation and Language.