RequirementClassifier

Version: 27

Model Description

This model is a fine-tuned BERT model for binary classification of software requirements. It classifies text as either "requirement" or "non-requirement".

Intended Uses

• Classify software requirement documents
• Identify requirement vs non-requirement statements
• Automated requirement extraction from documents

Training Data

The model was trained on the PROMISE NFR dataset with additional non-requirement examples.

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

# Load model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("rajinikarcg/RequirementClassifier")
model = AutoModelForSequenceClassification.from_pretrained("rajinikarcg/RequirementClassifier")

# Prepare input
text = "The system shall respond within 2 seconds"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=128)

# Get prediction
with torch.no_grad():
    outputs = model(**inputs)
    logits = outputs.logits
    prediction = torch.argmax(logits, dim=-1).item()

# Map to label
labels = ["non-requirement", "requirement"]
print(f"Prediction: {labels[prediction]}")

Version History

• 27: Latest version

Citation

If you use this model, please cite the PROMISE NFR dataset.