A team is training a language model on a massive, unlabeled corpus of text from the internet. Their training objective is to randomly mask 15% of the words in each input sentence and require the model to predict the original masked words. Which of the following statements best analyzes why this specific training method is considered 'self-supervised'?

Pre-training Strategy for a Specialized Domain

Designing a Self-Supervised Task for Code

Training Process for Text-to-Text Models