home edit page issue tracker
This page pertains to UD version 2.

UD Old Georgian GLC

Language: Old Georgian (code: oge)
Family: Kartvelian

This treebank has been part of Universal Dependencies since the UD v2.18 release.

The following people have contributed to making this treebank part of UD: Irina Lobzhanidze.

Repository: UD_Old_Georgian-GLC
Search this treebank on-line: PML-TQ
Download all treebanks: UD 2.19

License: CC BY-SA 4.0

Genre: fiction

Questions, comments? General annotation questions (either Old Georgian-specific or cross-linguistic) can be raised in the main UD issue tracker. You can report bugs in this treebank in the treebank-specific issue tracker on Github. If you want to collaborate, please contact [irina_lobzhanidze (æt) iliauni • edu • ge]. Development of the treebank happens directly in the UD repository, so you may submit bug fixes as pull requests against the dev branch.

Annotation Source
Lemmas assigned by a program, with some manual corrections, but not a full manual verification
UPOS annotated manually in non-UD style, automatically converted to UD, with some manual corrections of the conversion
XPOS assigned by a program, with some manual corrections, but not a full manual verification
Features assigned by a program, with some manual corrections, but not a full manual verification
Relations assigned by a program, with some manual corrections, but not a full manual verification

Description

The Old Georgian UD Treebank (UD_Old_Georgian-GLC) is the first syntactically annotated corpus of Georgian, based on a collection of annotated sentences selected from the Old Georgian Language Corpus (OGLC) available at https://oge.iliauni.edu.ge/.

The Old Georgian UD Treebank (UD_Old_Georgian-GLC) serves as the first syntactically annotated corpus of the Old Georgian language. It includes 1232 utterances (33630 tokens) selected from the OGLC (Doborjginidze et al. 2013), providing detailed annotations encompassing the grammatical structure and dependencies within the sentences.

Text Date Tokens Sentences
The Great Nomocanon: Cyril of Alexandria’s Epistle to Domnus 883 6575 151
The Great Nomocanon: Decree of the Council of Constantinople (394) 883 615 14
Gregory of Nazianzus, On the Resurrection 10th–11th c. 7804 322
Martyrdom of Barlaam the Ascetic 11th c. 5623 188
Andrew of Crete, On the Nativity of the Theotokos 11th c. 4585 188
On the Exaltation of the Life-Giving Cross 11th c. 2637 122
Book of Baruch 12th c. 4154 184
Epistle to the Antiochians by Ignatius the God-Bearer 12th–13th c. 1486 63
Total   33479 1232

The treebank’s annotations align with the Universal Dependencies (UD) specifications, allowing for greater consistency and compatibility with other UD treebanks. Although the tokenization and segmentation principles of the original GLC corpus differ slightly from those of the UD, the UD_Old_Georgian-GLC treebank adopts UD-compliant tokenization and segmentation principles, including the treatment of multiword tokens.

Morpho-syntactic annotations, as discussed in Lobzhanidze (2022), have been automatically adapted to UD requirements. This includes annotations for lemmas (LEMMA), part-of-speech categories (UPOS; XPOS), morphological features (FEATS), transliteration, and tokenization issues (MISC). Furthermore, heads of words (HEADS), dependency relations (DEPREL), and enhanced dependency graphs (DEPS) were automatically converted and then reviewed and manually corrected.

The current treebank is divided into three datasets for training, development, and evaluation, following the Universal Dependencies framework.

Training set (train): 734 sentences, 20937 syntactic words.

Development set (dev): 122 sentences, 2577 syntactic words.

Test set (test): 376 sentences, 10116 syntactic words.

Acknowledgments

The UD_Old_Georgian-GLC release is based on the data from the Georgian Language Corpus (GLC) developed with the financial support of the Shota Rustaveli National Science Foundation (Project Nos. DP2016_23, LE/17/1-30/13, AR/320/4-105/11, Y-04-10).

Special gratitudes goes to Prof. Dr. Dan Zeman for his invaluable contributions in making the language and dataset available on GitHub and offering valuable suggestions.

References

Doborjginidze, N., Lobzhanidze. (2012-2026). Georgian language corpus. See, https://oge.iliauni.edu.ge/. Accessed 18 April 2026.

Doborjginidze, N., Lobzhanidze, I., Mirianashvili, G. (2014). Corpus of Georgian Chronicles. See, http://corpora.iliauni.edu.ge/. Accessed 18 April 2026.

Lobzhanidze, I. (2022). Finite-State Computational Morphology: An Analyzer and Generator for Georgian. Cham: Springer.

Statistics of UD Old Georgian GLC

POS Tags

ADJ – ADP – ADV – AUX – CCONJ – INTJ – NOUN – NUM – PART – PRON – PROPN – PUNCT – SCONJ – VERB – X

Features

AdpType – AdvType – Aspect – Case – Case[stack] – Case[stackb] – Degree – Evident – ExtPos – Mood – NameType – Number – Number[io] – Number[obj] – Number[subj] – NumForm – NumType – PartType – Person – Person[io] – Person[obj] – Person[subj] – Poss – PronType – PunctSide – PunctType – Subcat – Tense – Typo – VerbForm – VerbType – Voice

Relations

acl – acl:relcl – advcl – advmod – advmod:emph – advmod:neg – amod – appos – case – cc – ccomp – compound – conj – cop – csubj – dep – det – det:poss – discourse – dislocated – fixed – flat – goeswith – iobj – mark – nmod – nsubj – nsubj:pass – nummod – obj – obl – orphan – parataxis – punct – root – vocative – xcomp

Tokenization and Word Segmentation

Morphology

Tags

Nominal Features

Degree and Polarity

Verbal Features

Pronouns, Determiners, Quantifiers

Other Features

Syntax

Auxiliary Verbs and Copula

Core Arguments, Oblique Arguments and Adjuncts

Here we consider only relations between verbs (parent) and nouns or pronouns (child).

Relations Overview