Too Long; Didn't Read
An article explaining the intuition behind the “positional embedding” in transformer models from the renowned research paper - “Attention Is All You Need”. An article explains the intuition. The concept of embedding in NLP is a process used in natural language processing for converting raw text into mathematical vectors. Embedding is to make the neural network understand the ordering and positional dependency in the sentence. This is because a machine learning model will not be able to directly consume an input in text format for the various computational processes.