Tongfei Chen

Researcher in #NLProc; Functional programmer @scala_lang; {Natural | Programming} language enthusiast; NLP/ML/PL. Tweets are my own

[Yunmo Chen @YunmoChen]

📢 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! 🚀

[Tongfei Chen @ctongfei]

@martinmbauer Évariste Galois has an h-index of 5.

[Tongfei Chen @ctongfei]

@xtimv @thomasahle Unpopular opinion: All math notations should be 0-indexed. \sum_0^n should be applied to {0, 1, ..., n-1}.

[Tongfei Chen @ctongfei]

@ruyimarone @SashaMTL FP additions are not associative?? 🤯

[Tongfei Chen @ctongfei]

@lidangzzz @MinakoOikawa One could contemporaneously publish two papers that mutually cite each other

[Tongfei Chen @ctongfei]

@rendu_a Seems like that the language is set to German?

[Tongfei Chen @ctongfei]

Wrote a little package that visualizes directed acyclic graphs (DAGs) in the terminal.
PyPI: https://t.co/Li4qaSuKjA GitHub: https://t.co/emnqgXTBQF

[Tongfei Chen @ctongfei]

As a τ-ist I insist that the correct form of this formula is e^iτ = 1.

[Tivadar Danka @TivadarDanka]

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:

[Tongfei Chen @ctongfei]

@xtimv @mrdrozdov No it does nit. “min=” doesn’t even pass the lexer.

[Tongfei Chen @ctongfei]

@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.

[Tongfei Chen @ctongfei]

Wordle 212 5/6

🟩⬛⬛⬛🟩
🟩⬛⬛⬛🟩
🟩⬛🟩⬛🟩
🟩⬛🟩⬛🟩
🟩🟩🟩🟩🟩

[Tongfei Chen @ctongfei]

@michaelzlin Likely the strawberry tree?

[Tongfei Chen @ctongfei]

@sjmielke Mine was Borland Delphi

[Tongfei Chen @ctongfei]

@Ted_Underwood @xtimv

[Tongfei Chen @ctongfei]

@Charlotte_Kao 怎麼了？

[Tongfei Chen @ctongfei]

Log is a linear operator 😛

[Tongfei Chen @ctongfei]

@wittgen_ball @keiskS Definitely! And stay cool!

[Tongfei Chen @ctongfei]

@keiskS I’m still in Baltimore, but will move to Seattle soon!

[Tongfei Chen @ctongfei]

@bokane Tensor Mandarin!