Concept

Auto-Encoding (AE) Models

This type of LM destroys the input text (e.g. masking words in sentence and trying to reconstruct the original text). It aims to build bidirectional encoding representations of the entire sentences, so infrastructures often correspond to the encoder part of transformer, where all input can be accessed at each location. They have been fine-tuned successfully for downstream tasks. Examples include BERT, ROBERTA, ERNIE, and applications are suitable for NLU tasks like sentence classification and sequence labeling.

0

1

Updated 2022-11-19

Tags

Deep Learning (in Machine learning)

Data Science