Login / Signup
BERT-NAR-BERT: A Non-Autoregressive Pre-Trained Sequence-to-Sequence Model Leveraging BERT Checkpoints.
Mohammad Golam Sohrab
Masaki Asada
Matiss Rikters
Makoto Miwa
Published in:
IEEE Access (2024)
Keyphrases
</>
autoregressive
probabilistic model
higher order
em algorithm
non stationary
random fields
neural network
image processing
multiscale
multiresolution
parameter estimation
maximum entropy
gaussian markov random field