TiBERT: A Non-autoregressive Pre-trained Model for Text Editing.

Baoxin Wang Ziyue Wang Wanxiang Che Dayong Wu Rui Zhang Bo Wang Shijin Wang

Published in: NLPCC (3) (2023)

Keyphrases

autoregressive
gaussian markov random field
non stationary
moving average
feature selection
face recognition
training data
bayesian networks
prior knowledge
model selection
visual information