Wine is not v i n. On the Compatibility of Tokenizations across Languages.

Antonis Maronikolakis Philipp Dufter Hinrich Schütze

Published in: EMNLP (Findings) (2021)

Keyphrases

language identification
english text
real world
data sets
databases
database
real time
machine learning
decision trees
multiscale
artificial neural networks
information retrieval systems
linguistic resources