Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: hun
|
| 3 |
+
license: cc-by-4.0
|
| 4 |
+
tags:
|
| 5 |
+
- word2vec
|
| 6 |
+
datasets: Hungarian_CoNLL17_corpus
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
## Information
|
| 10 |
+
A word2vec model trained by Andrey Kutuzov (andreku@ifi.uio.no) on a vocabulary of size 2702663 corresponding to 1694170960 tokens from the dataset `Hungarian_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_49", 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/20/49.zip
|