Recipes for Sequential Pre-training of Multilingual Encoder and Seq2Seq Models.

Saleh Soltan Andy Rosenbaum Tobias Falke Qin Lu Anna Rumshisky Wael Hamza

Published in: CoRR (2023)

Keyphrases

structured prediction
prior knowledge
experimental data
probabilistic model
statistical models
model selection
supervised learning
artificial neural networks
bayesian networks
learning algorithm
data sets
training set
training samples
complex systems
search engine
classification models
neural network