|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- ar |
|
|
base_model: |
|
|
- aubmindlab/bert-base-arabertv02 |
|
|
pipeline_tag: token-classification |
|
|
--- |
|
|
|
|
|
# SWEET<sub>NoPnx</sub> QALB-2014 Model |
|
|
|
|
|
## Model Description |
|
|
`CAMeL-Lab/text-editing-qalb14-nopnx` is a text editing model tailored for grammatical error correction (GEC) in Modern Standard Arabic (MSA). |
|
|
The model is based on [AraBERTv02](https://huggingface.co/aubmindlab/bert-base-arabertv02), which we fine-tuned using the [QALB-2014](https://camel.abudhabi.nyu.edu/qalb-shared-task-2015/) dataset. |
|
|
This model was introduced in our ACL 2025 paper, [Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study](https://arxiv.org/abs/2503.00985), where we refer to it as SWEET (Subword Edit Error Tagger). |
|
|
|
|
|
The model was fine-tuned to fix non-punctuation (i.e., NoPnx) errors. Details about the training procedure, data preprocessing, and hyperparameters are available in the paper. |
|
|
The fine-tuning code and associated resources are publicly available on our GitHub repository: https://github.com/CAMeL-Lab/text-editing. |
|
|
|
|
|
|
|
|
|
|
|
## Intended uses |
|
|
To use the `CAMeL-Lab/text-editing-qalb14-nopnx` model, you must clone our text editing [GitHub repository](https://github.com/CAMeL-Lab/text-editing) and follow the installation requirements. |
|
|
We used this SWEET<sub>NoPnx</sub> model to report results on the QALB-2014 dev and test sets in our [paper](https://arxiv.org/abs/2503.00985). |
|
|
This model is intended to be used with SWEET<sub>Pnx</sub> ([`CAMeL-Lab/text-editing-qalb14-pnx`](https://huggingface.co/CAMeL-Lab/text-editing-qalb14-pnx)) model. |
|
|
|
|
|
## How to use |
|
|
Clone our text editing [GitHub repository](https://github.com/CAMeL-Lab/text-editing) and follow the installation requirements |
|
|
|
|
|
```python |
|
|
from transformers import BertTokenizer, BertForTokenClassification |
|
|
import torch |
|
|
import torch.nn.functional as F |
|
|
from gec.tag import rewrite |
|
|
|
|
|
|
|
|
nopnx_tokenizer = BertTokenizer.from_pretrained('CAMeL-Lab/text-editing-qalb14-nopnx') |
|
|
nopnx_model = BertForTokenClassification.from_pretrained('CAMeL-Lab/text-editing-qalb14-nopnx') |
|
|
|
|
|
pnx_tokenizer = BertTokenizer.from_pretrained('CAMeL-Lab/text-editing-qalb14-pnx') |
|
|
pnx_model = BertForTokenClassification.from_pretrained('CAMeL-Lab/text-editing-qalb14-pnx') |
|
|
|
|
|
|
|
|
def predict(model, tokenizer, text, decode_iter=1): |
|
|
for _ in range(decode_iter): |
|
|
tokenized_text = tokenizer(text, return_tensors="pt", is_split_into_words=True) |
|
|
with torch.no_grad(): |
|
|
logits = model(**tokenized_text).logits |
|
|
preds = F.softmax(logits.squeeze(), dim=-1) |
|
|
preds = torch.argmax(preds, dim=-1).cpu().numpy() |
|
|
edits = [model.config.id2label[p] for p in preds[1:-1]] |
|
|
|
|
|
assert len(edits) == len(tokenized_text['input_ids'][0][1:-1]) |
|
|
subwords = tokenizer.convert_ids_to_tokens(tokenized_text['input_ids'][0][1:-1]) |
|
|
text = rewrite(subwords=[subwords], edits=[edits])[0][0] |
|
|
return text |
|
|
|
|
|
|
|
|
text = 'يجب الإهتمام ب الصحه و لا سيما ف ي الصحه النفسيه ياشباب المستقبل،،'.split() |
|
|
|
|
|
output_sent = predict(nopnx_model, nopnx_tokenizer, text, decode_iter=2) |
|
|
output_sent = predict(pnx_model, pnx_tokenizer, output_sent.split(), decode_iter=1) |
|
|
print(output_sent) # يجب الاهتمام بالصحة ولا سيما في الصحة النفسية يا شباب المستقبل . |
|
|
|
|
|
``` |
|
|
|
|
|
## Citation |
|
|
```bibtex |
|
|
@inter{alhafni-habash-2025-enhancing, |
|
|
title={Enhancing Text Editing for Grammatical Error Correction: Arabic as a Case Study}, |
|
|
author={Bashar Alhafni and Nizar Habash}, |
|
|
year={2025}, |
|
|
eprint={2503.00985}, |
|
|
archivePrefix={arXiv}, |
|
|
primaryClass={cs.CL}, |
|
|
url={https://arxiv.org/abs/2503.00985}, |
|
|
} |
|
|
``` |
|
|
|
