Skip to content

jpeckenpaugh/nexttext

Repository files navigation

nexttext

Take your text to the next level.

nexttext is a lightweight Python toolkit for neutralizing and re-framing text to reduce noise, hidden skew, and unwanted artifacts in your AI pipelines.

It works equally well on input labels (human-annotated training data) and generated labels (outputs from captioning or classification models), helping you build systems that are more reliable, consistent, and testable.


✨ Features

  • 🧹 Debias → Neutralize gendered or stereotypical language automatically
  • 🔄 Rebias → Reintroduce controlled skew for testing and validation, with optional context-aware strategies
  • 📊 Works for both training data and model outputs
  • ⚡ Simple API with no heavy dependencies
  • 🔓 Open-source under a permissive license (MIT)

📦 Installation

pip install nexttext

🚀 Quick Start

>>> from nexttext import debias, rebias

>>> labels = [
...   "A man seated at a table talking to a young girl.",
...   "A girl kneeling to receive communion. Her hands are folded in prayer.",
...   "A doctor speaking with his patient while a nurse takes her vitals."
... ]

>>> debias(labels)
[
  "A person seated at a table talking to a child.",
  "A child kneeling to receive communion. Their hands are folded in prayer.",
  "A doctor speaking with a patient while a nurse takes vitals."
]

>>> rebias(["A person working on a car."])
["A man working on his car."]

# Context-aware rebiasing when you need it
>>> rebias(["A person holding a baby."], strategy="contextual")
["A woman holding a baby."]

# Round trip: neutralize, then reintroduce skew
>>> rebias(debias(["A woman holding a baby."]), strategy="contextual")
["A woman holding a baby."]

🛠 Use Cases

  • Training data cleanup → Reduce bias before it enters your models.
  • Inference filtering → Postprocess outputs for safer, more consistent results.
  • Validation & testing → Intentionally rebias text to stress-test robustness.
  • Standardization → Ensure consistent labels across diverse datasets.

🤝 Contributing

Contributions are welcome!
Please open an issue or a pull request to suggest improvements.


📄 License

nexttext is open-source software released under the MIT License.

About

nexttext is a lightweight Python toolkit for neutralizing explicit gendered terms in text. Via simple, fast heuristics it helps clean and standardize AI-generated labels, reducing model-induced misgendering and other unwanted linguistic artifacts. It's intended for use in AI pipelines, for both processing training data or filtering model outputs.

Topics

Resources

License

Stars

0 stars

Watchers

0 watching

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages