Enhancing Subword Embeddings with Open N-grams.

Csaba Veres Paul Kapustin

Published in: NLDB (2020)

Keyphrases

n gram
language model
text classification
bag of words
variable length
language modelling
language independent
vector space
inside outside algorithm
viterbi algorithm
language modeling
part of speech
word segmentation
character n grams
document retrieval
web documents
low dimensional
bayesian networks