Data

Tools

Indexes

Applications

Experiments

Open Source Science

odycy

A general-purpose NLP pipeline for Ancient Greek

https://github.com/centre-for-humanities-computing/odycy

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.1%) to scientific vocabulary

Keywords

ancient-greek machine-learning natural-language-processing nlp python spacy
Last synced: 6 months ago · JSON representation

Repository

A general-purpose NLP pipeline for Ancient Greek

Basic Info
Statistics
  • Stars: 22
  • Watchers: 0
  • Forks: 3
  • Open Issues: 5
  • Releases: 0
Topics
ancient-greek machine-learning natural-language-processing nlp python spacy
Created about 3 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License Citation

README.md

A general-purpose NLP pipeline for Ancient-Greek.


Features :mount_fuji:

  • [x] Part of speech tagging
  • [x] Lemmatization
  • [x] Dependency parsing
  • [x] Morphological analysis
  • [ ] Named entity recognition (work in progress :construction:)

Installation :sunrise:

OdyCy models can be directly installed from huggingface:

```bash

To install the transformer-based pipeline

pip install https://huggingface.co/chcaa/grcodycyjointtrf/resolve/main/grcodycyjointtrf-any-py3-none-any.whl

To install the tok2vec-based small pipeline

pip install https://huggingface.co/chcaa/grcodycyjointsm/resolve/main/grcodycyjointsm-any-py3-none-any.whl ```

Usage :whale:

Open in Colab

OdyCy pipelines can be imported with spaCy.

```python import spacy

For the transformer-based pipeline

nlp = spacy.load("grcodycyjoint_trf")

For a faster and smaller (but less accurate) tok2vec-based pipeline

nlp = spacy.load("grcodycyjoint_sm") ```

Pipelines can then be used as any other spaCy pipeline. (spaCy Documentation)

Check out our Documentation on Basic Usage.

Performance :boat:

odyCy achieves state of the art performance on multiple tasks on unseen test data from the Universal Dependencies Perseus treebank, and performs second best on the PROIEL treebanks test set on even more tasks. In addition performance also seems relatively stable across the two evaluation datasets in comparison with other NLP pipelines.

For plots and tables on OdyCy's performance, check out the Documentation page on Performance

Owner

  • Name: Center for Humanities Computing Aarhus
  • Login: centre-for-humanities-computing
  • Kind: organization
  • Email: chcaa@cas.au.dk
  • Location: Aarhus, Denmark

GitHub Events

Total
  • Issues event: 1
  • Watch event: 5
Last Year
  • Issues event: 1
  • Watch event: 5

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 46
  • Total pull requests: 15
  • Average time to close issues: 19 days
  • Average time to close pull requests: 1 day
  • Total issue authors: 3
  • Total pull request authors: 2
  • Average comments per issue: 0.74
  • Average comments per pull request: 0.13
  • Merged pull requests: 15
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 2
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 2
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • jankounchained (25)
  • Urdatorn (1)
  • gcelano (1)
Pull Request Authors
  • jankounchained (10)
  • x-tabdeveloping (1)
Top Labels
Issue Labels
enhancement (8) low-priority (6) data (4) bug (4) dependencies (2) wontfix (1) documentation (1) parameters (1)
Pull Request Labels

Dependencies

requirements_packaging.txt pypi
  • pandas *
  • pytest >=7.2.0,<8.0.0
  • spacy >=3.5.0,<3.6.0
  • spacy-huggingface-hub >=0.0.8,<0.1.0
  • wheel >=0.38.0,<0.39.0
requirements_preprocessing.txt pypi
  • colorama >=0.4.0,<0.5.0
  • lxml >=4.9.2,<4.10.0
  • pandas >=1.5.1,<1.6.0
  • pytest >=7.2.0,<8.0.0
requirements_training.txt pypi
  • numpy >=1.17.0,<1.24.0
  • pytest >=7.2.0,<8.0.0
  • spacy >=3.5.0,<3.6.0
  • spacy-transformers >=1.1.7,<1.2.0
  • wandb >=0.13.7,<0.14
.github/workflows/static.yml actions
  • actions/checkout v3 composite
  • actions/configure-pages v2 composite
  • actions/deploy-pages v1 composite
  • actions/upload-pages-artifact v1 composite