la_vectors_floret_lg

la_vectors_floret_lg

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

Part of the LatinCy project — pretrained NLP pipelines for Latin.

Overview

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

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

Usage

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.

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:

Parameters

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

Citation

If you use these vectors, please cite this preprint:

@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 — Medium vectors (50k buckets)
• LatinCy pipelines — Latin NLP pipelines for spaCy 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.