Single or Double: On Number of Classifier Layers for Small Language Models.

Muhammed Cihat Ünal Munes Zaval Aydin Gerek

Published in: SIU (2023)

Keyphrases

language model
language modeling
n gram
document retrieval
feature selection
probabilistic model
decision trees
speech recognition
relevance model
language modelling
bayesian networks
feature space
training set
information extraction
document ranking
ad hoc information retrieval