# MultiEL
Multilingual Entity Linking model by BELA model
This project want to create easy-to-use Multilingual Entity Linking model by BELA model.
**Origin Project**
- Bi-encoder Entity Linking Architecture (BELA): [https://github.com/facebookresearch/BELA](https://github.com/facebookresearch/BELA)
## Install
> pip install multiel
## Usage
```python
from multiel import BELA
bela_run = BELA(device="cuda")
print(bela_run.process_batch(["นายกประยุทธ์ประกาศจัดการเลือกตั้ง"]))
```
output:
```python
[{'offsets': [0], 'lengths': [12], 'entities': ['Q2108126'], 'md_scores': [0.22365164756774902], 'el_scores': [0.6967974901199341]}]
```
#### API
```python
from multiel import BELA
BELA(
md_threshold:float=0.2,
el_threshold:float=0.4,
checkpoint_name: str="wiki",
device: str="cuda:0",
config_name:str="joint_el_mel_new",
repo:str="wannaphong/BELA"
)
```
- md_threshold: md threshold
- el_threshold: Entity Linking threshold
- checkpoint_name: checkpoint name (wiki, aida, mewsli, and e2e) or your file name with extension
- device: device
- config_name: config name (in the BELA project)
- repo: Huggingface Hub repo (Default [wannaphong/BELA](https://huggingface.co/wannaphong/BELA))
**Predict**
```python
BELA.process_batch([str, str])
```
## License
MIT license and the model is MIT license. ([BELA is MIT licensed](https://github.com/facebookresearch/BELA/blob/main/LICENSE))
Raw data
{
"_id": null,
"home_page": "https://github.com/wannaphong/MultiEL",
"name": "MultiEL",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.6",
"maintainer_email": "",
"keywords": "NLP,natural language processing,text analytics,text processing,localization,computational linguistics",
"author": "Wannaphong",
"author_email": "wannaphong@yahoo.com",
"download_url": "https://files.pythonhosted.org/packages/49/79/47ab743a239de6ff22795b884aff8be8e1029aa9b66aea58d538420e20af/MultiEL-0.5.tar.gz",
"platform": null,
"description": "# MultiEL\nMultilingual Entity Linking model by BELA model\n\nThis project want to create easy-to-use Multilingual Entity Linking model by BELA model.\n\n**Origin Project**\n\n- Bi-encoder Entity Linking Architecture (BELA): [https://github.com/facebookresearch/BELA](https://github.com/facebookresearch/BELA)\n\n\n## Install\n\n> pip install multiel\n\n## Usage\n\n```python\nfrom multiel import BELA\n\nbela_run = BELA(device=\"cuda\")\n\nprint(bela_run.process_batch([\"\u0e19\u0e32\u0e22\u0e01\u0e1b\u0e23\u0e30\u0e22\u0e38\u0e17\u0e18\u0e4c\u0e1b\u0e23\u0e30\u0e01\u0e32\u0e28\u0e08\u0e31\u0e14\u0e01\u0e32\u0e23\u0e40\u0e25\u0e37\u0e2d\u0e01\u0e15\u0e31\u0e49\u0e07\"]))\n```\n\noutput:\n```python\n[{'offsets': [0], 'lengths': [12], 'entities': ['Q2108126'], 'md_scores': [0.22365164756774902], 'el_scores': [0.6967974901199341]}]\n```\n\n#### API\n\n```python\nfrom multiel import BELA\n\nBELA(\n md_threshold:float=0.2,\n el_threshold:float=0.4, \n checkpoint_name: str=\"wiki\", \n device: str=\"cuda:0\",\n config_name:str=\"joint_el_mel_new\",\n repo:str=\"wannaphong/BELA\"\n)\n```\n\n- md_threshold: md threshold\n- el_threshold: Entity Linking threshold\n- checkpoint_name: checkpoint name (wiki, aida, mewsli, and e2e) or your file name with extension\n- device: device\n- config_name: config name (in the BELA project)\n- repo: Huggingface Hub repo (Default [wannaphong/BELA](https://huggingface.co/wannaphong/BELA))\n\n**Predict**\n\n```python\nBELA.process_batch([str, str])\n```\n\n## License\n\nMIT license and the model is MIT license. ([BELA is MIT licensed](https://github.com/facebookresearch/BELA/blob/main/LICENSE))\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "Multilingual Entity Linking model by BELA model",
"version": "0.5",
"project_urls": {
"Bug Reports": "https://github.com/wannaphong/MultiEL/issues",
"Homepage": "https://github.com/wannaphong/MultiEL",
"Source": "https://github.com/wannaphong/MultiEL"
},
"split_keywords": [
"nlp",
"natural language processing",
"text analytics",
"text processing",
"localization",
"computational linguistics"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9a5753c07bf769067c8ebdb352d356fa75040aa7a91226aca4504e6c07ad9767",
"md5": "7e413b4676f07ef0faf3030b8723df87",
"sha256": "c036e85f7f048339bdcdcf8401beca484351bbf9440d80cbf5ac8000ec465ec2"
},
"downloads": -1,
"filename": "MultiEL-0.5-py3-none-any.whl",
"has_sig": false,
"md5_digest": "7e413b4676f07ef0faf3030b8723df87",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.6",
"size": 4226920,
"upload_time": "2023-06-29T12:25:00",
"upload_time_iso_8601": "2023-06-29T12:25:00.869663Z",
"url": "https://files.pythonhosted.org/packages/9a/57/53c07bf769067c8ebdb352d356fa75040aa7a91226aca4504e6c07ad9767/MultiEL-0.5-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "497947ab743a239de6ff22795b884aff8be8e1029aa9b66aea58d538420e20af",
"md5": "b80dec996a94c97ed11a7955b0f522a4",
"sha256": "0aee992a50cb1632323bc327288f4f6c14e444f12cb7af4dd5f1790641e82718"
},
"downloads": -1,
"filename": "MultiEL-0.5.tar.gz",
"has_sig": false,
"md5_digest": "b80dec996a94c97ed11a7955b0f522a4",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.6",
"size": 4141387,
"upload_time": "2023-06-29T12:25:03",
"upload_time_iso_8601": "2023-06-29T12:25:03.562757Z",
"url": "https://files.pythonhosted.org/packages/49/79/47ab743a239de6ff22795b884aff8be8e1029aa9b66aea58d538420e20af/MultiEL-0.5.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-06-29 12:25:03",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "wannaphong",
"github_project": "MultiEL",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "faiss-gpu",
"specs": []
},
{
"name": "fairscale",
"specs": []
},
{
"name": "hydra-core",
"specs": []
},
{
"name": "hydra-submitit-launcher",
"specs": []
},
{
"name": "pyyaml",
"specs": []
},
{
"name": "pytorch-lightning",
"specs": []
},
{
"name": "transformers",
"specs": []
},
{
"name": "tqdm",
"specs": []
},
{
"name": "sentencepiece",
"specs": []
},
{
"name": "h5py",
"specs": []
},
{
"name": "protobuf",
"specs": [
[
"==",
"3.20"
]
]
},
{
"name": "ujson",
"specs": []
},
{
"name": "huggingface_hub",
"specs": []
},
{
"name": "accelerate",
"specs": [
[
">=",
"0.9.0"
]
]
}
],
"lcname": "multiel"
}
JSON
