Improving Tokenisation by Alternative Treatment of Spaces.

Edward Gow-Smith Harish Tayyar Madabushi Carolina Scarton Aline Villavicencio

Published in: EMNLP (2022)

Keyphrases

real time
digital libraries
lower bound
neural network
genetic algorithm
data sets
databases
learning algorithm
information systems
website
multiscale
artificial neural networks
hidden markov models