Timo Schick (@timo_schick) / X

Attentive Mimicking: Better Word Embeddings by Attending to Informative Contexts - ACL Anthology

Timo Schick (@timo_schick) / X

Timo Schick on X: 🎉 With quite some delay, I'm happy to annouce that Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification (w/ Helmut Schmid & @HinrichSchuetze) has

BERTRAM: Improved Word Embeddings Have Big Impact on Contextualized Model Performance - ACL Anthology

Emanuele Vivoli (@EmanueleVivoli) / X

Fabio Petroni (@Fabio_Petroni) / X

Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference - ACL Anthology

Timo Schick (@timo_schick) / X

timoschick (Timo Schick)

Alexandre Salle (@alexsalle) / X

Timo Schick (@timo_schick) / X

Timo Schick on X: 🎉 New paper 🎉 We show that language models are few-shot learners even if they have far less than 175B parameters. Our method performs similar to @OpenAI's GPT-3

Timo Schick (@timo_schick) / X

timoschick (Timo Schick)