🔥 Just Released: Free guide to 💪 training LLMs, including techniques for parallelization, tokenization strategies and their tradeoffs, plus how much data you'll actually need 🤯
#MII2023 Boeker @TU_Muenchen: GeMTeX klinisches Referenz-Korpus der #MII mit Textdaten als Ressource für die Forschung. Semantische Annotationen; trainierte Sprachmodelle; algorithmische Auswertung; Nutzung #NLP in #DIZ. Vorteile der semantischen Textanalyse für die Versorgung💪
This week I've introduced DOPA METER - DOPA METER - A Tool Suite for Metrical Document Profiling and Aggregation at #EMNLP2023 Demo #Singapore.
https://t.co/S5PQlPJ8ec
@emnlpmeeting Thanks for the great venue!
Prof @chrmanning is giving the last keynote of #EMNLP2023 to a full house, on “Academic NLP research in the Age of LLMs: Nothing but blue skies!”
@emnlpmeeting
The @PyDataNYC video from "Half hour of labeling power: Can we beat GPT?" by @ryanwesslen & me is now live!
We show how to use LLMs to speed up annotation, collect 1.2k examples & beat our few-shot baseline.
📺 Video: https://t.co/9AOffwymfy
📝 Slides: https://t.co/ViPoMwklEO