Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- word2vec
|
4 |
+
language: fr
|
5 |
+
license: cc-by-3.0
|
6 |
+
datasets:
|
7 |
+
- wikipedia
|
8 |
+
---
|
9 |
+
|
10 |
+
### Description
|
11 |
+
|
12 |
+
A French word2vec model trained on [frwiki](https://dumps.wikimedia.org/frwiki/) by Fauconnier with the following hyperparameters:
|
13 |
+
lem: no, pos: no, phrase: no, train: cbow, dim: 1000, cutoff: 200
|
14 |
+
|
15 |
+
|
16 |
+
### How to use?
|
17 |
+
|
18 |
+
```
|
19 |
+
from gensim.models import KeyedVectors
|
20 |
+
from huggingface_hub import hf_hub_download
|
21 |
+
model = KeyedVectors.load_word2vec_format("Word2vec/fauconnier_frWiki_no_phrase_no_postag_1000_skip_cut200.bin", binary=True, unicode_errors="ignore")
|
22 |
+
model.most_similar("intéressant_a")
|
23 |
+
```
|
24 |
+
|
25 |
+
### Citation
|
26 |
+
```
|
27 |
+
@misc{fauconnier_2015,
|
28 |
+
author = {Fauconnier, Jean-Philippe},
|
29 |
+
title = {French Word Embeddings},
|
30 |
+
url = {http://fauconnier.github.io},
|
31 |
+
year = {2015}}
|
32 |
+
```
|