We want a number to let the computer understand us.

For that, we want to convert words into numeric representations (vectors or matrices).

If you are converting text into numerical embeddings you have 2 options →

1. Statistical Methods
   1. BagOfWords
   2. TF-IDF
2. ML/DL Based Methods
   1. Lookup method
   2. Word2Vec (Word to Vector) → Continuous BagOfWords
   3. Transformer Based Architectures

1 → Statistical Methods

Bag-Of-Words

Consider these 2 sentences

the cat sat on the mat

the dog sat on the cat