metadata
tags:
- word2vec
language: fr
license: cc-by-3.0
Description
A French word2vec model trained on FrWac by Fauconnier with the following hyperparameters: lem: no, pos: no, phrase: no, train: skip, dim: 500, cutoff: 200
How to use?
from gensim.models import KeyedVectors
from huggingface_hub import hf_hub_download
model = KeyedVectors.load_word2vec_format("Word2vec/fauconnier_frWiki_no_phrase_no_postag_1000_skip_cut200.bin", binary=True, unicode_errors="ignore")
model.most_similar("intéressant_a")
Citation
@misc{fauconnier_2015,
author = {Fauconnier, Jean-Philippe},
title = {French Word Embeddings},
url = {http://fauconnier.github.io},
year = {2015}}