Learn Before
Example

Example of Sentinel Masking in Denoising Autoencoding

Sentinel masking is a denoising autoencoding task where corrupted spans in the input are replaced by special sentinel tokens, such as [X] and [Y]. For instance, an input sequence might be corrupted to [C] The kitten [X] the [Y]. The encoder-decoder model is then trained to predict only the masked portions, outputting a sequence that reconstructs the missing tokens associated with each sentinel, such as [X] is chasing [Y] ball ..

0

1

Updated 2026-04-17

Contributors are:

Who are from:

Tags

Foundations of Large Language Models

Ch.1 Pre-training - Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences