Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship?

Sathvik Nair Philip Resnik

Published in: EMNLP (Findings) (2023)

Keyphrases

n gram
text classification
data mining
website
keywords
probabilistic model
language independent
multiword
word forms
hidden markov models
web search
language model
related words
note taking
syntactic categories