Model Card for Sentence-ALDi
A BERT-based model fine-tuned to estimate the Arabic Level of Dialectness of text.
Model | Link on ๐ค |
---|---|
Sentence-ALDi (random seed: 42) | https://huggingface.co/AMR-KELEG/Sentence-ALDi |
Sentence-ALDi (random seed: 30) | https://huggingface.co/AMR-KELEG/Sentence-ALDi-30 |
Sentence-ALDi (random seed: 50) | https://huggingface.co/AMR-KELEG/Sentence-ALDi-50 |
Token-DI (random seed: 42) | https://huggingface.co/AMR-KELEG/ALDi-Token-DI |
Token-DI (random seed: 30) | https://huggingface.co/AMR-KELEG/ALDi-Token-DI-30 |
Token-DI (random seed: 50) | https://huggingface.co/AMR-KELEG/ALDi-Token-DI-50 |
Usage
from transformers import AutoTokenizer, AutoModelForSequenceClassification
model_name = "AMR-KELEG/Sentence-ALDi"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)
def compute_score(sentence):
inputs = tokenizer(sentence, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
return min(max(0, logits[0][0].item()), 1)
if __name__ == "__main__":
s1 = "ุงูุทูุณ ุฌูุฏ ุงูููู
"
s2 = "ุงูุฌู ุญูู ุงูููุงุฑุฏุฉ"
print(s1, round(compute_score(s1), 3)) # 0
print(s2, round(compute_score(s2), 3)) # 0.951
Model Description
- Model type: Regression head on top of a BERT-based model fine-tuned for estimating the Arabic Level of Dialectness of text.
- Language(s) (NLP): Arabic.
- Finetuned from model : MarBERT
Citation
If you find the model useful, please cite the following respective paper:
@inproceedings{keleg-etal-2023-aldi,
title = "{ALD}i: Quantifying the {A}rabic Level of Dialectness of Text",
author = "Keleg, Amr and
Goldwater, Sharon and
Magdy, Walid",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.655",
doi = "10.18653/v1/2023.emnlp-main.655",
pages = "10597--10611",
abstract = "Transcribed speech and user-generated text in Arabic typically contain a mixture of Modern Standard Arabic (MSA), the standardized language taught in schools, and Dialectal Arabic (DA), used in daily communications. To handle this variation, previous work in Arabic NLP has focused on Dialect Identification (DI) on the sentence or the token level. However, DI treats the task as binary, whereas we argue that Arabic speakers perceive a spectrum of dialectness, which we operationalize at the sentence level as the Arabic Level of Dialectness (ALDi), a continuous linguistic variable. We introduce the AOC-ALDi dataset (derived from the AOC dataset), containing 127,835 sentences (17{\%} from news articles and 83{\%} from user comments on those articles) which are manually labeled with their level of dialectness. We provide a detailed analysis of AOC-ALDi and show that a model trained on it can effectively identify levels of dialectness on a range of other corpora (including dialects and genres not included in AOC-ALDi), providing a more nuanced picture than traditional DI systems. Through case studies, we illustrate how ALDi can reveal Arabic speakers{'} stylistic choices in different situations, a useful property for sociolinguistic analyses.",
}
- Downloads last month
- 11,347
Inference API (serverless) has been turned off for this model.