Fine-tuning Machine Learning with Humanities Data: Creating Ground Truth Annotations (i.e. Labeled Data)

As most of us will probably know by now, machine learning has become a big part of digital humanities projects, especially in the computational humanities, and more and more people are trying to implement it. It’s becoming increasingly accessible, even to people who don’t have massive machine learning skills, and more and more people are getting involved in these projects. Most people have a broad idea of how machine learning works. I have this old blog post on it—although I suppose now I could write a better one; maybe I will at some point—but you will find enough introductions out there on how machine learning works. TLDR: This post covers making your own labeled data for machine learning in Humanities contexts (more conceptually and less practically than How to create your own fine-tuning or training dataset for computer vision using Supervisely) and specifically, how much time to budget and how to go about it according to me. There’s more to

read more Fine-tuning Machine Learning with Humanities Data: Creating Ground Truth Annotations (i.e. Labeled Data)

See also: Original Source by The LaTeX Ninja