Could you provide an overview of the Skip-gram model and its rationale behind generating word embeddings?

Skip-gram is a type of neural network architecture used for learning word embeddings in NLP.
The rationale behind Skip-gram is to predict the context words (words surrounding a target word) given a target word. The model learns to represent words in a continuous vector space where similar words are closer to each other.
By training on a large corpus of text, Skip-gram captures the semantic relationships between words, allowing for tasks such as word similarity and analogy.