Sentence-ALDi-30

Model Card for Sentence-ALDi-30

<!-- Provide a quick summary of what the model is/does. -->

A BERT-based model fine-tuned to estimate the Arabic Level of Dialectness of text.

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
model_name = "AMR-KELEG/Sentence-ALDi-30"

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 = "الطقس جيد اليوم"
  s2 = "الجو حلو النهاردة"

  print(s1, round(compute_score(s1), 3)) # 0
  print(s2, round(compute_score(s2), 3)) # 0.951

Model Description

<!-- Provide a longer summary of what this model is. --> <!-- - **Developed by:** Amr Keleg -->

• 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.

<!--- **License:** [More Information Needed] -->

• Finetuned from model: MarBERT
• Dataset: AOC-ALDi

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.",
}