README.md

---
language:
  - la
license: mit
library_name: spacy
tags:
  - spacy
  - floret
  - word-vectors
  - latin
  - nlp
---

# la_vectors_floret_lg

Floret word vectors for Latin (large, 200k hash buckets, 300 dimensions).

Part of the [LatinCy](https://github.com/diyclassics/latincy) project — pretrained NLP pipelines for Latin.

## Overview

| Feature | Value |
|---------|-------|
| **Type** | Floret (hash-based subword embeddings) |
| **Dimensions** | 300 |
| **Hash buckets** | 200,000 |
| **Algorithm** | CBOW |
| **Language** | Latin (`la`) |
| **spaCy version** | `>=3.8.11,<3.9.0` |
| **License** | MIT |

Floret vectors use hash-based subword embeddings, meaning **every word gets a vector** — there are no out-of-vocabulary words. This is especially important for morphologically rich languages like Latin. The large variant uses 200k hash buckets (vs 50k for medium), reducing hash collisions for finer-grained distinctions.

## Installation

```bash
pip install https://huggingface.co/latincy/la_vectors_floret_lg/resolve/main/la_vectors_floret_lg-3.10.0-py3-none-any.whl
```

## Usage

```python
import spacy

nlp = spacy.load("la_vectors_floret_lg")

# Get word vectors
doc = nlp("rex populum regit")
for token in doc:
    print(token.text, token.vector[:5])

# Compute similarity
doc1 = nlp("bellum")
doc2 = nlp("pugna")
print(doc1.similarity(doc2))
```

These vectors are primarily intended as a component in LatinCy pipelines (`la_core_web_lg`), but can also be used standalone.

## Evaluation

All methods were trained on the same v3.10 corpus and scored on the same benchmark (v0.2: 1,545 analogy items, 1,285 odd-one-out items).

> **Note:** v0.2 is a **development benchmark**, not a finalized release benchmark — these numbers are for cross-method comparison and may change.

| Model | Analogy Rank 1 | Analogy Rank 5 | Odd-One-Out |
|-------|---------------|---------------|-------------|
| FastText CBOW-300-10 | **76.2%** | **91.5%** | 70.3% |
| **Floret (lg)** | 74.3% | 89.7% | 68.5% |
| Floret (md) | 73.4% | 88.2% | 65.7% |
| Word2Vec CBOW-300-10 | 42.3% | 71.0% | **77.3%** |
| GloVe 300 | 16.3% | 34.1% | 66.4% |

Floret is competitive with FastText on analogies while being 6x smaller and supporting arbitrary vocabulary, which is why we have chosen to use the Floret vectors for pipeline training.

## Training

### Corpus

Trained on 14.3M sentences (278M tokens) from 15 sources:

| Source | Description |
|--------|-------------|
| CC100-Latin | Web-crawled Latin text (deduplicated and filtered) |
| Latin Wikisource | General Latin texts |
| Latin Wikipedia | Latin Wikipedia articles |
| The Latin Library | General Latin texts |
| Patrologia Latina | Patristic texts |
| CAMENA Neo-Latin | Early modern Latin texts |
| CLTK-Tesserae Latin | Classical texts |
| Perseus Digital Library | Classical texts |
| CSEL | Corpus Scriptorum Ecclesiasticorum Latinorum (patristic) |
| digilibLT | Late-antique Latin texts |
| UD + LASLA treebanks | Annotated treebank sentences |
| Formulae | Early medieval legal formulae |
| EDH | Epigraphic Database Heidelberg (inscriptions) |
| Epistolae | Medieval Latin letters |
| PTA | Patristic Text Archive |

### Parameters

| Parameter | Value |
|-----------|-------|
| Algorithm | CBOW |
| Dimensions | 300 |
| Subword n-gram range | 3–6 |
| Hash buckets | 200,000 |
| Epochs | 15 |
| Negative sampling | 25 |
| Min count | 50 |
| Learning rate | 0.05 |

Training followed Sprugnoli et al. 2019 for epoch count and negative sampling parameters.

## Citation

If you use these vectors, please cite this preprint:

```bibtex
@misc{burns2023latincy,
    title = "{LatinCy}: Synthetic Trained Pipelines for {L}atin {NLP}",
    author = "Burns, Patrick J.",
    year = "2023",
    eprint = "2305.04365",
    archivePrefix = "arXiv",
    primaryClass = "cs.CL",
    url = "https://arxiv.org/abs/2305.04365"
}
```

## See also

- [la_vectors_floret_md](https://huggingface.co/latincy/la_vectors_floret_md) — Medium vectors (50k buckets)
- [LatinCy pipelines](https://huggingface.co/latincy) — Latin NLP pipelines for [spaCy](https://spacy.io/) using these vectors

## References

- Sprugnoli, R., Passarotti, M., and Moretti, G. 2019. "Vir Is to Moderatus as Mulier Is to Intemperans Lemma Embeddings for Latin." In *Proceedings of the Sixth Italian Conference on Computational Linguistics*. Bari, Italy. 1–7. http://ceur-ws.org/Vol-2481/paper69.pdf.