pay-freq-v2

pay-freq-v2 is a fine-tuned multi-class sequence classification model designed to determine the frequency at which a wage is reportedly paid (i.e., hourly, weekly, monthly, or annually). It is built on top of a deberta-v3-base model.

Basic Usage

The model can be used with the standard text-classification pipeline.

from transformers import pipeline, AutoModelForSequenceClassification, AutoTokenizer

model_name = "loyoladatamining/pay-freq-v2"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name, max_length=128, truncation=True)

# Create text classification pipeline
nlp = pipeline(
    "text-classification", 
    model=model, 
    tokenizer=tokenizer,
    max_length=128,
    truncation=True
)

# Inference
text = "Employees earn $45.00 per hour in this role."
result = nlp(text)
print(result)

Output Format

The model returns a classification dictionary containing the predicted frequency label and the associated probability score:

[
  {
    "label": "hourly",
    "score": 0.9876
  }
]

Citation

If you find pay-freq-v2 useful in your work, please consider citing:

@article{meisenbacher2025extracting,
  title={Extracting O* NET Features from the NLx Corpus to Build Public Use Aggregate Labor Market Data},
  author={Meisenbacher, Stephen and Nestorov, Svetlozar and Norlander, Peter},
  year={2025}
}