On the N-gram Approximation of Pre-trained Language Models.

Aravind Krishnan Jesujoba O. Alabi Dietrich Klakow

Published in: CoRR (2023)

Keyphrases

language model
n gram
pre trained
language modeling
training data
document retrieval
probabilistic model

language modelling
query expansion
test collection
retrieval model
language independent
bag of words
training examples

speech recognition
information retrieval
vector space model
document ranking
out of vocabulary
query terms
training set

word segmentation
statistical language modeling
pseudo relevance feedback
cross lingual
active learning
question answering