Neutralizing Subjectivity Bias with HuggingFace Transformers

The NLP task of text style transfer (TST) aims to automatically control the style attributes of a piece of text while preserving the content, which is an important consideration for making NLP more user-centric.

In this research report, I explore text style transfer through an applied use case — neutralizing subjectivity bias in free text. I start by providing an introduction to TST as a task and its potential use cases. I then describe the applied use case, dataset, modeling approach, and present a set of custom, reference-free evaluation metrics for quantifying model performance without labels. I also include a discussion of ethics centered around my prototype: Exploring Intelligent Writing Assistance.

Checkout the report, blog, code, and HuggingFace artifacts for more details!