Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
language: bg
|
4 |
+
tags:
|
5 |
+
- embeddings
|
6 |
+
- glove
|
7 |
+
- cc100
|
8 |
+
license: cc-by-sa-4.0
|
9 |
+
---
|
10 |
+
|
11 |
+
# CC100 GloVe Embeddings for BG Language
|
12 |
+
|
13 |
+
## Model Description
|
14 |
+
- **Language:** bg
|
15 |
+
- **Embedding Algorithm:** GloVe (Global Vectors for Word Representation)
|
16 |
+
- **Vocabulary Size:** 3917287
|
17 |
+
- **Vector Dimensions:** 300
|
18 |
+
- **Training Data:** CC100 dataset
|
19 |
+
|
20 |
+
## Training Information
|
21 |
+
We trained GloVe embeddings using the original C code. The model was trained by stochastically sampling nonzero elements from the co-occurrence matrix, over 100 iterations, to produce 300-dimensional vectors. We used a context window of ten words to the left and ten words to the right. Words with fewer than 5 co-occurrences were excluded for languages with over 1 million tokens in the training data, and the threshold was set to 2 for languages with smaller datasets.
|
22 |
+
|
23 |
+
We used data from CC100 for training the static word embeddings. We set xmax = 100, α = 3/4, and used AdaGrad optimization with an initial learning rate of 0.05.
|
24 |
+
|
25 |
+
## Usage
|
26 |
+
These embeddings can be used for various NLP tasks such as text classification, named entity recognition, and as input features for neural networks.
|
27 |
+
|
28 |
+
## Citation
|
29 |
+
If you use these embeddings in your research, please cite:
|
30 |
+
|
31 |
+
```bibtex
|
32 |
+
@misc{gurgurov2024lowremrepositorywordembeddings,
|
33 |
+
title={LowREm: A Repository of Word Embeddings for 87 Low-Resource Languages Enhanced with Multilingual Graph Knowledge},
|
34 |
+
author={Daniil Gurgurov and Rishu Kumar and Simon Ostermann},
|
35 |
+
year={2024},
|
36 |
+
eprint={2409.18193},
|
37 |
+
archivePrefix={arXiv},
|
38 |
+
primaryClass={cs.CL},
|
39 |
+
url={https://arxiv.org/abs/2409.18193},
|
40 |
+
}
|
41 |
+
```
|
42 |
+
|
43 |
+
## License
|
44 |
+
These embeddings are released under the [CC-BY-SA 4.0 License](https://creativecommons.org/licenses/by-sa/4.0/).
|