Login / Signup

Effect of tokenization on transformers for biological sequences.

Edo DotanGal JaschekTal PupkoYonatan Belinkov
Published in: Bioinformatics (Oxford, England) (2024)
Code, data, and trained tokenizers are available on https://github.com/technion-cs-nlp/BiologicalTokenizers.
Keyphrases
  • electronic health record
  • resistance training
  • big data
  • body composition
  • deep learning