📢 Exciting News in NLP Metrics! 📊
🔍 There are a lot of different metrics for structured prediction tasks for NLP. Or are there? Our EMNLP 2023 paper suggests they might not be so different at all! Plus, we've got a great new Python library to help you make your own metrics! 🚀
What you see below is one of the most beautiful formulas in mathematics.
A single equation, establishing a relation between 𝑒, π, the imaginary number, and 1. It is mind-blowing.
This is what's behind the sorcery:
@xleaps @mrseaoxbleem These optimization techniques (quasi-Newton, trust-region methods, etc) usually require some estimation of the Hessian matrices, which are computationally infeasible for overparameterized neural nets.