|
--- |
|
license: mit |
|
datasets: |
|
- kargaranamir/HengamCorpus |
|
tags: |
|
- span-marker |
|
- token-classification |
|
- ner |
|
- named-entity-recognition |
|
pipeline_tag: token-classification |
|
inference: false |
|
language: |
|
- fa |
|
--- |
|
|
|
|
|
# Hengam: An Adversarially Trained Transformer for Persian Temporal Tagging |
|
|
|
# Usage |
|
|
|
You can use this model directly downloading the utils and requirements files and installing requirements: |
|
|
|
```python |
|
>>> ! wget https://huggingface.co/spaces/kargaranamir/Hengam/raw/main/utils.py |
|
>>> ! wget https://huggingface.co/spaces/kargaranamir/Hengam/raw/main/requirements.txt |
|
>>> ! pip install -r requirements.txt |
|
``` |
|
|
|
and downloading the models HengamTransA.pth or HengamTransW.pth and building ner pipline: |
|
|
|
```python |
|
>>> import torch |
|
>>> from huggingface_hub import hf_hub_download |
|
>>> from utils import * |
|
|
|
>>> # HengamTransW = hf_hub_download(repo_id="kargaranamir/Hengam", filename="HengamTransW.pth") |
|
>>> HengamTransA = hf_hub_download(repo_id="kargaranamir/Hengam", filename="HengamTransA.pth") |
|
``` |
|
|
|
```python |
|
>>> # ner = NER(model_path=HengamTransW, tags=['B-TIM', 'I-TIM', 'B-DAT', 'I-DAT', 'O']) |
|
>>> ner = NER(model_path=HengamTransA, tags=['B-TIM', 'I-TIM', 'B-DAT', 'I-DAT', 'O']) |
|
>>> ner('.سلام من و دوستم ساعت ۸ صبح روز سه شنبه رفتیم دوشنبه بازار ') |
|
|
|
[{'Text': 'ساعت', 'Tag': 'B-TIM', 'Start': 17, 'End': 21}, |
|
{'Text': '۸', 'Tag': 'I-TIM', 'Start': 22, 'End': 23}, |
|
{'Text': 'صبح', 'Tag': 'I-TIM', 'Start': 24, 'End': 27}, |
|
{'Text': 'روز', 'Tag': 'I-TIM', 'Start': 28, 'End': 31}, |
|
{'Text': 'سه', 'Tag': 'B-DAT', 'Start': 32, 'End': 34}, |
|
{'Text': 'شنبه', 'Tag': 'I-DAT', 'Start': 35, 'End': 39}] |
|
``` |
|
|
|
|
|
## Citation |
|
|
|
If you use any part of this repository in your research, please cite it using the following BibTex entry. |
|
```python |
|
@inproceedings{mirzababaei-etal-2022-hengam, |
|
title = {Hengam: An Adversarially Trained Transformer for {P}ersian Temporal Tagging}, |
|
author = {Mirzababaei, Sajad and Kargaran, Amir Hossein and Sch{\"u}tze, Hinrich and Asgari, Ehsaneddin}, |
|
year = 2022, |
|
booktitle = {Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing}, |
|
publisher = {Association for Computational Linguistics}, |
|
address = {Online only}, |
|
pages = {1013--1024}, |
|
url = {https://aclanthology.org/2022.aacl-main.74} |
|
} |
|
``` |
|
|