Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: bul
|
3 |
+
license: cc-by-4.0
|
4 |
+
tags:
|
5 |
+
- word2vec
|
6 |
+
datasets: Bulgarian_CoNLL17_corpus
|
7 |
+
---
|
8 |
+
|
9 |
+
## Information
|
10 |
+
A word2vec model trained by Andrey Kutuzov (andreku@ifi.uio.no) on a vocabulary of size 628026 corresponding to 388433724 tokens from the dataset `Bulgarian_CoNLL17_corpus`.
|
11 |
+
The model is trained with the following properties: no lemmatization and postag with the algorith Word2Vec Continuous Skipgram with window of 10 and dimension of 100.
|
12 |
+
|
13 |
+
## How to use?
|
14 |
+
```
|
15 |
+
from gensim.models import KeyedVectors
|
16 |
+
from huggingface_hub import hf_hub_download
|
17 |
+
model = KeyedVectors.load_word2vec_format(hf_hub_download(repo_id="Word2vec/nlpl_33", filename="model.bin"), binary=True, unicode_errors="ignore")
|
18 |
+
```
|
19 |
+
|
20 |
+
## Citation
|
21 |
+
Fares, Murhaf; Kutuzov, Andrei; Oepen, Stephan & Velldal, Erik (2017). Word vectors, reuse, and replicability: Towards a community repository of large-text resources, In Jörg Tiedemann (ed.), Proceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, 22-24 May 2017. Linköping University Electronic Press. ISBN 978-91-7685-601-7
|
22 |
+
|
23 |
+
This archive is part of the NLPL Word Vectors Repository (http://vectors.nlpl.eu/repository/), version 2.0, published on Friday, December 27, 2019.
|
24 |
+
Please see the file 'meta.json' in this archive and the overall repository metadata file http://vectors.nlpl.eu/repository/20.json for additional information.
|
25 |
+
The life-time identifier for this model is: http://vectors.nlpl.eu/repository/20/33.zip
|