---
tags:
- spacy
- token-classification
- ancient-greek
language:
- grc
license: mit
model-index:
- name: grc_dep_web_md
  results:
  - task:
      name: POS Tagging
      type: token-classification
    metrics:
    - name: POS Accuracy
      type: accuracy
      value: 0.9175
    - name: TAG (XPOS) Accuracy
      type: accuracy
      value: 0.9154
  - task:
      name: Lemmatization
      type: token-classification
    metrics:
    - name: Lemma Accuracy
      type: accuracy
      value: 0.9359
  - task:
      name: Dependency Parsing
      type: token-classification
    metrics:
    - name: Labeled Attachment Score
      type: f_score
      value: 0.6731
---

# grc_dep_web_md

**Ancient Greek** pipeline for [spaCy](https://spacy.io), part of the [LatinCy](https://huggingface.co/latincy) project.

**Experimental beta release.** This is part of the first generation of Ancient Greek models porting the [LatinCy](https://huggingface.co/latincy) Latin pipeline infrastructure to Ancient Greek. Expect rough edges; scores and component behavior will improve as training data is harmonized and curated through the LatinCy flywheel (train, evaluate, curate, retrain).

Medium model with 50,000-key floret vectors (300 dimensions). Trained on Universal Dependencies Ancient Greek treebanks (PTNK, PROIEL, Perseus) with a 1.2M-entry lookup lemmatizer overlay built from CLTK Morpheus, UD treebanks, and Wiktionary.

| Feature | Description |
| --- | --- |
| **Name** | `grc_dep_web_md` |
| **Version** | `3.8.1` |
| **spaCy** | `>=3.8.11,<3.9.0` |
| **Default Pipeline** | `senter`, `tok2vec`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `lookup_lemmatizer`, `parser` |
| **Components** | `senter`, `tok2vec`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `lookup_lemmatizer`, `parser` |
| **Vectors** | floret, 50,000 unique vectors (300 dimensions) |
| **License** | `MIT` |
| **Author** | [Patrick J. Burns](https://huggingface.co/latincy) |

## Install

```bash
pip install https://huggingface.co/latincy/grc_dep_web_md/resolve/main/grc_dep_web_md-3.8.1-py3-none-any.whl
```

## Usage

```python
import spacy

nlp = spacy.load("grc_dep_web_md")
doc = nlp("\u03bc\u1fc6\u03bd\u03b9\u03bd \u1f04\u03b5\u03b9\u03b4\u03b5 \u03b8\u03b5\u1f70 \u03a0\u03b7\u03bb\u03b7\u03ca\u03ac\u03b4\u03b5\u03c9 \u1f08\u03c7\u03b9\u03bb\u1fc6\u03bf\u03c2")

for token in doc:
    print(token.text, token.pos_, token.lemma_, token.dep_)
```

## Evaluation

Scores on held-out UD test data (combined PTNK + PROIEL + Perseus).

| Metric | Score |
| --- | --- |
| **POS (UPOS) Accuracy** | 91.75 |
| **TAG (XPOS) Accuracy** | 91.54 |
| **Morph (UFeats) Accuracy** | 81.32 |
| **Lemma Accuracy** | 93.59 |
| **Unlabeled Attachment Score (UAS)** | 75.71 |
| **Labeled Attachment Score (LAS)** | 67.31 |
| **Sentences F-Score** | 88.18 |

## Training Data

| Source | Description |
| --- | --- |
| [UD_Ancient_Greek-PTNK](https://github.com/UniversalDependencies/UD_Ancient_Greek-PTNK) | Septuagint (Codex Alexandrinus) |
| [UD_Ancient_Greek-PROIEL](https://github.com/UniversalDependencies/UD_Ancient_Greek-PROIEL) | PROIEL Ancient Greek treebank |
| [UD_Ancient_Greek-Perseus](https://github.com/UniversalDependencies/UD_Ancient_Greek-Perseus) | Perseus Ancient Greek treebank |

## Components

- **tok2vec** -- Shared token-to-vector encoder (CNN, width 96)
- **tagger** -- Fine-grained POS tagger (XPOS, harmonized 16-tag tagset)
- **morphologizer** -- Morphological feature assignment (UPOS + UFeats)
- **trainable_lemmatizer** -- Edit-tree lemmatizer
- **lookup_lemmatizer** -- 1.2M-entry dictionary lemmatizer overlay (CLTK Morpheus + UD + Wiktionary); normalizes grave accents to acute at query time
- **parser** -- Dependency parser (transition-based)
- **senter** -- Sentence segmenter

## Label Scheme

<details>

<summary>View label scheme (1796 labels for 3 components)</summary>

**`tagger`**: `adjective`, `adverb`, `conjunction`, `conjunction_adverb`, `conjunction_pronoun`, `determiner`, `interjection`, `noun`, `number`, `particle`, `preposition`, `pronoun`, `proper_noun`, `punc`, `unknown`, `verb`

**`morphologizer`**: 1749 morphological feature combinations

**`parser`**: `ROOT`, `acl`, `advcl`, `advmod`, `amod`, `appos`, `aux`, `case`, `cc`, `ccomp`, `conj`, `cop`, `csubj`, `dep`, `det`, `discourse`, `dislocated`, `fixed`, `flat`, `iobj`, `mark`, `nmod`, `nsubj`, `nummod`, `obj`, `obl`, `orphan`, `parataxis`, `punct`, `vocative`, `xcomp`

</details>