A fast and flexible architecture for very large word n-gram datasets.

Published in: Nat. Lang. Eng. (2013)

Keyphrases

n gram
language model
language independent
bag of words
text classification
word segmentation
part of speech
variable length
language modeling
character n grams
viterbi algorithm
language modelling
inside outside algorithm
web documents
word level
out of vocabulary
statistical language modeling
decision trees