I opted for bluesky @lernerp.bsky.social. It seems that both can be seamlessly connected via Bridgy Fed. Mastodon should follow @bsky.brid.gy and Bluesky should follow @ap.brid.gy.

any thoughts on mastodon vs bluesky?.

"Cette publication annule et remplace celle du terme « causette » au Journal officiel du 16 mars 1999." 🥲.

😶.

RT @MelMitchell1: @DrJimFan tokenization -> string theory.

Training my first DPO model, I feel like I've finally entered the 21st century.

RT @mlia_isir: "Vers la traduction automatique des néologismes scientifiques".by @_lerner_paul and @yvofr .Published as a long paper with o….

how is it possible that fastText ( does not cite GloVe?.

from Manning's NLP class at Stanford 🍦

Great introduction to NLP by Jurafsky, Daniel and Martin, James H.

In the Field

RT @kchonyc: no, a checkerboard background is not a transparent background, @ChatGPTapp 🤦

RT @kchonyc: we all quote Firth for "You shall know a word by the company it keeps!" perfectly fine, as he indeed said so in his book. but….

first I'm like: "what?!" then I realize my chatbot ideas have not evolved much in 5 years🤦‍♂️

I spent 1h setting up vllm and inference time reduced from 6h to 3min 🥲 (although I was already using 8bit quantization, not sure where the dark magic is coming from).

"Instead, part of the ‘unacceptability’ of mat is incorrectly carried over to P(␣in | I ␣was ␣a ␣mat), where ␣in competes for probability mass against the highly likely ron".

"P(␣mat ron | I ␣was ␣a) is factorized into P(␣mat | I ␣was ␣a) · P(ron | I ␣was ␣a ␣mat), and therefore it follows that P(␣mat ron | I ␣was ␣a) ≤ P(␣mat | I ␣was ␣a), despite the fact that matron is more acceptable than mat in the above context.".

RT @thibaudmulier: Ces enseignants-chercheurs ont choisi d'exercer une deuxième activité en dehors de l'université - L'Etudiant https://t.c….

was published four days after but has the same finding