Login / Signup

How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese.

Takuro FujiiKoki ShibataAtsuki YamaguchiTerufumi MorishitaYasuhiro Sogawa
Published in: CoRR (2023)
Keyphrases
  • case study
  • databases
  • supply chain
  • test bed
  • real world
  • expressive power
  • machine learning
  • artificial intelligence
  • computer vision
  • feature selection
  • decision trees
  • bayesian networks
  • grammatical inference